Method, device and computer equipment for identifying the operating state of a cement firing system

Abstract

The application discloses a kind of identification method, device and computer equipment of cement firing system operating state.The method comprises: obtaining the real-time data segment of cement firing system, data segment includes the data of multiple characteristic parameters;Data segment is preprocessed and normalized;The corresponding value range of each characteristic parameter in data segment after normalization is divided into regions;The data of each characteristic parameter in data segment after normalization is located in the corresponding coding of region, and the data of each characteristic parameter in data segment is identified, to obtain the corresponding coding string of data segment;The corresponding coding string of data segment is output, and the real-time operating state of cement firing system is identified.The application can quantitatively represent the operating state of cement firing system at each moment, does not involve the labeling of sample and the training of model, can reduce the workload of artificial, while avoiding the problem that judgment accuracy is not enough.

Description

Technical Field

[0001] This application relates to the field of cement production technology, and in particular to a method, apparatus and computer equipment for identifying the operating status of a cement firing system. Background Technology

[0002] A cement calcination system consists of multiple pieces of equipment operating simultaneously, resulting in a very close coupling between the processes within the system. Cement raw materials, after being ground, enter the calcination system, where numerous physicochemical reactions occur, ultimately forming cement clinker. Because the cement clinker production process is lengthy and influenced by many factors, the cement calcination system requires monitoring of numerous processes, involves complex reactions, and operates under various conditions.

[0003] Specifically, such as Figure 1 As shown, the main equipment of the cement calcination system includes preheaters (C1-C5), a decomposition furnace, a rotary kiln, and a grate cooler. The preheater's primary function is to dry and preheat the raw materials. The materials then enter the decomposition furnace for decomposition and dehydration before entering the rotary kiln for calcination. The rotary kiln is a high-energy-consuming cylindrical device with a certain angle of inclination. Powdered coal is ignited at the kiln head for heating, and electrical equipment supplies power to the kiln to make it rotate. The materials move to the kiln head by their own gravity and the rotational force of the kiln, where they undergo high-temperature heating to promote important chemical reactions in the cement raw materials, resulting in clinker. The clinker is then transported to the grate cooler for cooling. The energy sources for the cement calcination system are mainly coal and electricity. Coal is needed to heat the preheater section to promote decomposition, and coal is needed to heat the raw materials for calcination in the decomposition furnace section. The power supply system continuously supplies power to the rotary kiln to keep it rotating, allowing the materials to fully undergo chemical reactions.

[0004] When the production status of the cement calcination system fluctuates, timely manual intervention by the operator is necessary to ensure the normal operation of the production system and the quality of the produced products. However, varying operator levels of control over the production situation and their experience can lead to different control parameter settings and varying timeliness in judging different operating states of the calcination system. This can result in poor on-site performance, making it difficult to guarantee consistently stable production, and ultimately impacting the overall stability and economic efficiency of the system.

[0005] To address this issue, a solution has emerged that utilizes image processing and machine learning methods to analyze flame images. This involves using image segmentation techniques to obtain regions of interest from the flame images, extracting image features, and then using machine learning to build a state recognition model based on the extracted features. Finally, this model is used to identify the current state of the firing system.

[0006] However, in the methods described above, the images used for image segmentation and feature extraction must be labeled. Therefore, it's necessary to label images in different states. However, in actual production processes, there are no standardized labeled samples, requiring manual labeling, which leads to a significant workload. Furthermore, the sample size under normal production conditions far exceeds that under abnormal conditions, and this imbalance affects modeling, making it difficult to guarantee the model's accuracy. Additionally, due to the large lag characteristic of the cement firing process, adjusting control parameters after states such as "over-sintering," "red kiln," and "under-sintering" have formed is often insufficient to change the current system's operating state. Summary of the Invention

[0007] Based on this, and in response to the aforementioned technical problems, a method, apparatus, and computer device for identifying the operating status of a cement firing system are provided. This addresses the technical issues that existing methods for distinguishing the operating status of a cement firing system rely on manual labeling of samples, which involves a large workload, and that the samples are unbalanced, making it difficult to guarantee the accuracy of the judgment.

[0008] To achieve the above objectives, this application provides the following technical solution:

[0009] Firstly, a method for identifying the operating status of a cement firing system, comprising:

[0010] Acquire real-time data segments from a cement firing system, the data segments including data of multiple characteristic parameters;

[0011] The data fragments are preprocessed;

[0012] The preprocessed data segment is normalized so that the data of each feature parameter in the data segment is within a preset range.

[0013] The corresponding value range of each feature parameter in the normalized data segment is divided into regions, and the corresponding value range of each feature parameter in the normalized data segment is divided into multiple regions, each of which corresponds to a different code.

[0014] Determine the region where the data of each feature parameter in the normalized data segment is located, and use the corresponding code of the region where the data of each feature parameter in the normalized data segment is located to identify the data of each feature parameter in the data segment, thereby obtaining the corresponding code string of the data segment;

[0015] Output the corresponding encoded string of the data segment to identify the real-time operating status of the cement firing system.

[0016] Optionally, the plurality of characteristic parameters include the outlet pressure, outlet temperature, cone pressure, and cone feed temperature of all preheaters, and the outlet temperature, outlet pressure, tertiary air temperature, tertiary air duct pressure, outlet nitrogen oxide emissions, and outlet carbon monoxide emissions of the decomposition furnace.

[0017] Optionally, the preprocessing of the data segment includes:

[0018] Determine whether the data of each feature parameter in the data segment is continuous;

[0019] When it is determined that there are discontinuous feature parameters, it is determined whether the duration of the null value of the discontinuous feature parameter is less than a preset time threshold; if the duration of the null value of the discontinuous feature parameter is less than the preset time threshold, the discontinuous feature parameters in the data segment are filled in.

[0020] Zero-phase filtering is applied to some feature parameters in the data segment.

[0021] Alternatively, cubic spline interpolation can be used to complete the discontinuous feature parameters in the data segment.

[0022] Further, optionally, the preprocessing of the data segment further includes:

[0023] The data of some feature parameters in the data segment are merged, averaged, or the maximum / minimum value is taken to form a data segment containing new feature parameters.

[0024] Optionally, the preprocessed data segment can be normalized using a robust normalization method or a max-min normalization method.

[0025] Optionally, the method further includes:

[0026] Determine whether the corresponding encoding string of the data segment at each time step changes with the corresponding encoding string of the data segment at the previous time step, and whether the corresponding encoding of the data of a single feature parameter changes simultaneously.

[0027] If the code of a single feature parameter changes, or the codes of multiple feature parameters change simultaneously, then the current operating state of the cement firing system is determined to be abnormal.

[0028] Secondly, a device for indicating the operating status of a cement firing system includes:

[0029] The data fragment acquisition module is used to acquire real-time data fragments of the cement firing system, wherein the data fragments include data of multiple characteristic parameters;

[0030] A preprocessing module is used to preprocess the data fragments;

[0031] The normalization processing module is used to normalize the preprocessed data segment so that the data of each feature parameter in the data segment is within a preset range.

[0032] The region division module is used to divide the corresponding value range of each feature parameter in the normalized data segment into regions, and divides the corresponding value range of each feature parameter in the normalized data segment into multiple regions, each of which corresponds to a different code.

[0033] The encoding module is used to determine the region where the data of each feature parameter in the normalized data segment is located, and to identify the data of each feature parameter in the data segment by using the corresponding encoding of the region where the data of each feature parameter in the normalized data segment is located, thereby obtaining the corresponding encoding string of the data segment.

[0034] The encoding string output module is used to output the corresponding encoding string of the data segment to identify the real-time operating status of the cement firing system.

[0035] Thirdly, a computer device includes a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the method described in any one of the first aspects.

[0036] Fourthly, a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in any one of the first aspects.

[0037] The present invention has at least the following beneficial effects:

[0038] In the method for identifying the operating status of a cement firing system provided in this embodiment of the invention, real-time data segments of the cement firing system are acquired, preprocessed, and normalized. Then, the corresponding value range of each feature parameter in the normalized data segment is divided into regions. The corresponding code of the region where each feature parameter's data is located in the normalized data segment is used to identify the data of each feature parameter in the data segment, ultimately obtaining the corresponding code string of the data segment. This method utilizes statistical analysis to perform statistical analysis on each feature parameter in the data segment, and then encodes and marks each feature parameter in each data segment. Thus, the corresponding code string of each data segment accurately identifies the operating status of the cement firing system at each moment, enabling operators to promptly identify whether the operating status of the cement firing system has changed, promoting intelligent control of the cement firing system. The method provided in this embodiment of the invention does not involve sample labeling or model training, thus reducing manual workload and avoiding the problem of insufficient model accuracy due to sample imbalance. This method can quantitatively represent the operating status of the cement firing system at each moment, avoiding the problem of untimely adjustment of control parameters caused by different operators' varying sensitivities to changes in the production site status. Attached Figure Description

[0039] Figure 1 This is a process flow diagram of a cement firing system;

[0040] Figure 2 A flowchart illustrating a method for identifying the operating status of a cement firing system according to an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the cubic spline interpolation method;

[0042] Figure 4 This is an example diagram of data segment encoding in one embodiment of the present invention;

[0043] Figure 5 This is another flowchart illustrating a method for identifying the operating status of a cement firing system according to an embodiment of the present invention.

[0044] Figure 6 A modular architecture block diagram of a device for indicating the operating status of a cement firing system, provided in one embodiment of the present invention;

[0045] Figure 7 This is an internal structural diagram of a computer device provided in one embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0047] In one embodiment, such as Figure 1 As shown, a method for identifying the operating status of a cement firing system is provided, including the following steps:

[0048] S1, acquire real-time data segments of the cement firing system, which include data on multiple characteristic parameters.

[0049] Real-time data snippets are retrieved from the database and passed to the data preprocessing program.

[0050] The characteristic parameters contained in the data segments are the key variables of the cement firing system that need to be monitored. Specifically, multiple characteristic parameters include all preheaters ( Figure 1 The system includes 62 characteristics such as the outlet pressure, outlet temperature, cone pressure, and cone feeding temperature on both sides of C1-C5 in the decomposition furnace, as well as the outlet temperature, outlet pressure, tertiary air temperature, tertiary air duct pressure, outlet nitrogen oxide (NOx) emission, and outlet carbon monoxide (CO) emission.

[0051] In other words, a data segment can be a data segment of size 3600*62 consisting of 3600 data points of the above 62 features.

[0052] S2, preprocesses the data fragments.

[0053] Furthermore, preprocessing of the data fragments includes:

[0054] Determine whether the data for each feature parameter in a data segment is continuous;

[0055] When it is determined that there are discontinuous feature parameters, it is determined whether the duration of the null value of the discontinuous feature parameter is less than a preset time threshold; if the duration of the null value of the discontinuous feature parameter is less than the preset time threshold, the discontinuous feature parameters in the data segment are filled in.

[0056] Zero-phase filtering is applied to some feature parameters in the data segment.

[0057] In this study, cubic spline interpolation was used to complete the discontinuous feature parameters in the data segment.

[0058] In other words, we check whether the time series data is continuous; if it is not continuous, we determine the duration of the break; if the break duration is short, meaning the duration of null values ​​in the data is short, we then use cubic spline interpolation to fill in the null values. We perform relevant processing on null and zero values ​​in the data segment. Because signals in industrial production sites may experience abrupt changes, some of which are actually spurious signals but can affect the frequency and amplitude of characteristic fluctuations, impacting subsequent data normalization and encoding, we perform filtering operations on certain features and smooth the data based on the changes in site characteristics.

[0059] Specifically, the cubic spline interpolation method is introduced as follows:

[0060] Piecewise interpolation, such as Figure 3 As shown, the known data is divided into several segments, each corresponding to a cubic function.

[0061] The cubic function for each segment is defined by the following equation:

[0062] S i (x)=a i +b i (xx i )+c i (xx i ) 2 +d i (xx i ) 3 i = 0, 1, ..., n-1

[0063] The mathematical expressions for the cubic function S(x) corresponding to n intervals are as follows:

[0064]

[0065] To ensure that the piecewise functions have zero-order continuity, first-order derivative continuity, second-order derivative continuity, and smooth connection at their junctions, solve for the coefficients in the above formula, and use the function for each interval to complete the missing data.

[0066] The zero-phase filtering is described below:

[0067] Since common filtering methods often cause data lag after filtering, a zero-phase bilateral filter is designed to solve this problem. The filter parameters are automatically set according to the fluctuation frequency and amplitude of different characteristics to separate the useful signal and improve the anti-interference ability of the data.

[0068] Zero-phase filtering first determines the initial conditions (coefficients) of the filter, then expands the beginning and end of the original sequence, passes the expanded sequence through the filter, reverses the result and passes it through the filter again, and finally reverses the result again and removes the expanded part at the beginning and end to obtain the output sequence after zero-phase filtering.

[0069] The filter processing within the filter is implemented using the filter's difference equations:

[0070]

[0071] Where a and b are the filter coefficients, x(n) is the nth input point, and y(n) is the nth output point.

[0072] Furthermore, the preprocessing operations also include:

[0073] By merging, averaging, or taking the maximum / minimum values ​​of some characteristic parameters in the data segment, a data segment containing new characteristic parameters can be formed that can more accurately represent the real-time operating status of the cement firing system.

[0074] In actual field operations, some features lack practical meaning and are unsuitable for direct modeling. Transforming these features to generate new ones yields more valuable information. This involves determining whether feature merging, averaging, or taking maximum / minimum values ​​is necessary based on the field characteristics. The goal is to construct new features that represent the current system operating status. For example, the difference between the outlet pressures of the third preheater C3 and the fourth preheater C4 can be used to determine if material blockage has occurred.

[0075] In summary, data preprocessing of the acquired data segments involves checking the temporal continuity of the data, handling null and zero values, filtering some features, and performing feature transformations, such as merging or taking the maximum or minimum values ​​of certain features, and constructing new features using some of the existing features.

[0076] S3 normalizes the preprocessed data segments so that the data of each feature parameter in the data segments are within a preset range.

[0077] Specifically, robust normalization or max-min normalization is used to normalize the preprocessed data segments. The preset interval can be, but is not limited to, [0,1].

[0078] In other words, normalizing data segments unifies the units of measurement, ensuring that each feature in the sample data falls within a specified range. This means that the range of data variation is kept within a fixed range, preparing for subsequent regional division.

[0079] S4. Divide the corresponding value range of each feature parameter in the normalized data segment into regions. Each feature parameter in the normalized data segment is divided into multiple regions, and each region corresponds to a different code.

[0080] Divide the normalized value range into regions. For example, if a feature value range in the data after max-min normalization is between [a, b], this range needs to be divided into n regions. The regions are divided according to the data distribution and the number of regions to be divided, and each of these n regions corresponds to a different code.

[0081] S5, determine the region where the data of each feature parameter in the normalized data segment is located, and use the corresponding code of the region where the data of each feature parameter in the normalized data segment is located to identify the data of each feature parameter in the data segment, and obtain the corresponding code string of the data segment.

[0082] In other words, the data is encoded by scaling each normalized data point according to the number of regions it is divided into. Then, the codes obtained for each feature are arranged in the order of the data features and combined together to obtain the encoded string corresponding to each sample data.

[0083] That is, the regions are divided according to the range of change of each feature after normalization, and the data is scaled according to the number of regions. Each feature of each sample data will get an encoding, and each sample data will get an encoding string arranged in the order of features.

[0084] S6 outputs the corresponding encoded string of the data segment, indicating the real-time operating status of the cement firing system.

[0085] Furthermore, the method also includes:

[0086] Determine whether the corresponding encoding string of the data segment at each time step changes with the corresponding encoding string of the data segment at the previous time step, and whether the corresponding encoding of the data of a single feature parameter changes simultaneously.

[0087] If the code of a single feature parameter changes, or the codes of multiple feature parameters change simultaneously, then the current operating state of the cement firing system is determined to be abnormal.

[0088] In other words, by checking the code corresponding to the sample data, it is possible to quantitatively determine whether the current sample data and the previous sample data are in the same operating state. If a single feature code changes significantly or the code values ​​of multiple features change simultaneously, it indicates that the current operating state of the system is different from before. This code string is the identifier of the operating state of the cement firing system.

[0089] like Figure 4 As shown, there are 4 data segments, each with 4 features, derived from... Figure 4 It can be seen that the first three data entries are encoded as "edca", while the fourth data entry is encoded as "cdca". The encoding of the fourth data entry is significantly different from that of the first three data entries, indicating that the current operating state of the system has changed compared to before. Based on the encoding, it can be determined that feature 1 has undergone a mutation.

[0090] Another flowchart illustrating the method provided in this embodiment can be found here. Figure 5 .

[0091] In the above-mentioned method for identifying the operating status of a cement firing system, the operating status of the system is identified by using statistical analysis to encode the data. The encoding method uses the range of variation of features to divide the region, determines the scaling ratio according to the divided region, scales the data according to the ratio, and then rounds it to obtain the digital code.

[0092] Different production states correspond to different ranges of change in the feature values ​​of the data samples. When the production state changes, the range of change of one or more feature values ​​changes significantly compared to the previous production state. Therefore, we can encode each feature according to its range of change, so that each data sample forms a code representing its current state. Thus, based on the corresponding code string of the cement firing system at each moment, the operating state of the cement firing system at each moment can be accurately identified, enabling operators to promptly identify whether the current operating state has changed and promoting the intelligent control of the cement firing system.

[0093] In the aforementioned method for identifying the operating status of a cement firing system, when the samples are imbalanced or the samples required for model building are unlabeled, statistical methods are used to perform statistical analysis on each variable in the samples. Then, each variable in each sample is coded and labeled, thereby accurately identifying different states that occur during system operation through the corresponding coded strings of the samples. This method moves from operators qualitatively judging the production status to automatically and quantitatively representing the current operating status, avoiding the problem of untimely adjustment of control parameters caused by different operators' varying sensitivities to changes in the production site status.

[0094] In summary, the above-mentioned method for identifying the operating status of a cement firing system does not require a high degree of sample balance or whether the samples are labeled; it does not involve model construction, training, or invocation, thus avoiding problems such as decreased model robustness caused by changes in data trends; it can quantitatively represent the current operating status code, can be compared with previous status codes, can clearly determine whether the status has changed, and can clearly identify the characteristics of the change, thus exhibiting strong interpretability.

[0095] It should be understood that, although Figure 2 and Figure 5 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 and Figure 5 At least some of the steps in the process may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but may be executed at different times. The execution order of these steps or stages is not necessarily sequential, but may be executed in turn or alternately with other steps or at least some of the steps or stages in other steps.

[0096] In one embodiment, such as Figure 6 As shown, a device for indicating the operating status of a cement firing system is provided, comprising the following program modules:

[0097] The data fragment acquisition module 601 is used to acquire real-time data fragments of the cement firing system. The data fragments include data of multiple characteristic parameters.

[0098] Preprocessing module 602 is used to preprocess data fragments;

[0099] The normalization processing module 603 is used to normalize the preprocessed data segment so that the data of each feature parameter in the data segment is within a preset range.

[0100] The region partitioning module 604 is used to partition the corresponding value range of each feature parameter in the normalized data segment into regions, and the corresponding value range of each feature parameter in the normalized data segment is divided into multiple regions, each region corresponding to a different code.

[0101] The encoding module 605 is used to determine the region where the data of each feature parameter in the normalized data segment is located, and to identify the data of each feature parameter in the data segment by using the corresponding encoding of the region where the data of each feature parameter in the normalized data segment is located, thereby obtaining the corresponding encoding string of the data segment.

[0102] The encoding string output module 606 is used to output the corresponding encoding string of the data segment to identify the real-time operating status of the cement firing system.

[0103] Specific limitations regarding the identification device for the operating status of a cement firing system can be found in the above description of the limitations for identifying the operating status of a cement firing system, and will not be repeated here. Each module in the aforementioned identification device for the operating status of a cement firing system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0104] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for identifying the operating status of a cement firing system. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0105] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0106] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program relating to all or part of the processes in the methods of the above embodiments.

[0107] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon relating to all or part of the processes in the methods of the above embodiments.

[0108] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0109] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for identifying the operating status of a cement firing system, characterized in that, include: Acquire real-time data segments from a cement firing system, the data segments including data of multiple characteristic parameters; The data fragments are preprocessed; The preprocessed data segment is normalized so that the data of each feature parameter in the data segment is within a preset range. The corresponding value range of each feature parameter in the normalized data segment is divided into regions, and the corresponding value range of each feature parameter in the normalized data segment is divided into multiple regions, each of which corresponds to a different code. Determine the region where the data of each feature parameter in the normalized data segment is located, and use the corresponding code of the region where the data of each feature parameter in the normalized data segment is located to identify the data of each feature parameter in the data segment, thereby obtaining the corresponding code string of the data segment; Output the corresponding encoded string of the data segment to identify the real-time operating status of the cement firing system; The preprocessing of the data segment includes: Determine whether the data of each feature parameter in the data segment is continuous; When it is determined that there are discontinuous feature parameters, it is determined whether the duration of the null value of the discontinuous feature parameter is less than a preset time threshold; if the duration of the null value of the discontinuous feature parameter is less than the preset time threshold, the discontinuous feature parameters in the data segment are filled in; the discontinuous feature parameters in the data segment are filled in using the cubic spline interpolation method. Zero-phase filtering is applied to some feature parameters in the data segment.

2. The method for identifying the operating status of a cement firing system according to claim 1, characterized in that, The multiple characteristic parameters include the outlet pressure, outlet temperature, cone pressure, and cone feeding temperature of all preheaters, and the outlet temperature, outlet pressure, tertiary air temperature, tertiary air duct pressure, outlet nitrogen oxide emissions, and outlet carbon monoxide emissions of the decomposition furnace.

3. The method for identifying the operating status of a cement firing system according to claim 1, characterized in that, The preprocessing of the data segment further includes: The data of some feature parameters in the data segment are merged, averaged, or the maximum / minimum value is taken to form a data segment containing new feature parameters.

4. The method for identifying the operating status of a cement firing system according to claim 1, characterized in that, The preprocessed data segment is normalized using a robust normalization method or a max-min normalization method.

5. The method for identifying the operating status of a cement firing system according to claim 1, characterized in that, The method further includes: Determine whether the corresponding encoding string of the data segment at each time step changes with the corresponding encoding string of the data segment at the previous time step, and whether the corresponding encoding of the data of a single feature parameter changes simultaneously. If the code of a single feature parameter changes, or the codes of multiple feature parameters change simultaneously, then the current operating state of the cement firing system is determined to be abnormal.

6. A device for indicating the operating status of a cement firing system, characterized in that, include: The data fragment acquisition module is used to acquire real-time data fragments of the cement firing system, wherein the data fragments include data of multiple characteristic parameters; A preprocessing module is used to preprocess the data fragments; The normalization processing module is used to normalize the preprocessed data segment so that the data of each feature parameter in the data segment is within a preset range. The region division module is used to divide the corresponding value range of each feature parameter in the normalized data segment into regions, and divides the corresponding value range of each feature parameter in the normalized data segment into multiple regions, each of which corresponds to a different code. The encoding module is used to determine the region where the data of each feature parameter in the normalized data segment is located, and to identify the data of each feature parameter in the data segment by using the corresponding encoding of the region where the data of each feature parameter in the normalized data segment is located, thereby obtaining the corresponding encoding string of the data segment. The encoding string output module is used to output the corresponding encoding string of the data segment to identify the real-time operating status of the cement firing system; The preprocessing of the data segment includes: Determine whether the data of each feature parameter in the data segment is continuous; When it is determined that there are discontinuous feature parameters, it is determined whether the duration of the null value of the discontinuous feature parameter is less than a preset time threshold; if the duration of the null value of the discontinuous feature parameter is less than the preset time threshold, the discontinuous feature parameters in the data segment are filled in; the discontinuous feature parameters in the data segment are filled in using the cubic spline interpolation method. Zero-phase filtering is applied to some feature parameters in the data segment.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images