Intelligent monitoring method and device for boiler state and electronic equipment

Abstract

The invention discloses a boiler state intelligent monitoring method and device and electronic equipment, and the method comprises the steps: collecting a to-be-processed data set in the operation process of a target boiler in real time; based on a pre-constructed target prediction model, performing prediction processing on the real-time input data at each data acquisition moment to obtain prediction output data corresponding to each data acquisition moment; determining a target residual error corresponding to the to-be-processed data group according to the real-time output data and the predicted output data corresponding to each data acquisition moment; and according to the target residual error and the target comparison threshold interval corresponding to the target residual error, the operation state of the target boiler is determined. According to the invention, the operation state of the boiler is automatically subjected to anomaly detection, so that the detection efficiency and the detection accuracy are improved, and the abnormal operation state of the boiler is found in time.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment abnormality detection, and in particular to an intelligent monitoring device and electronic equipment for boiler status. Background Art

[0002] As an important equipment in industrial production, the normal operation of boilers is crucial to ensuring production safety and efficiency.

[0003] Since there are various abnormal conditions during the operation of the boiler, such as boiler overheating, abnormal water level or incomplete combustion, if these abnormal conditions are not discovered in time, it may lead to equipment failure or even accidents, causing serious economic losses and safety hazards. At present, the abnormal detection of the operating status of the boiler usually relies on manual experience or rules, which has problems such as low detection accuracy and untimely abnormal detection.

[0004] In order to more accurately determine whether there is any abnormality in the operating status of the boiler, it is necessary to improve the intelligent monitoring method of the boiler status. Summary of the invention

[0005] The present invention provides an intelligent monitoring device and electronic equipment for boiler status to solve the problems in the prior art of inaccurate detection results and untimely detection of abnormal status of the boiler when the operating status of the boiler is detected based on manual experience or rules.

[0006] In a first aspect, an embodiment of the present invention provides an intelligent monitoring method for a boiler state, comprising:

[0007] Collecting in real time a data group to be processed during the operation of the target boiler; wherein the data group to be processed includes at least one real-time input data and real-time output data corresponding to a data collection moment;

[0008] Based on the pre-built target prediction model, the real-time input data at each data collection moment is predicted and processed to obtain the predicted output data corresponding to each data collection moment;

[0009] Determining the target residual corresponding to the data group to be processed according to the real-time output data and the predicted output data corresponding to each of the data collection moments;

[0010] The operating state of the target boiler is determined according to the target residual and the target comparison threshold interval corresponding to the target residual.

[0011] In a second aspect, an embodiment of the present invention further provides a method and device for intelligently monitoring a boiler state, comprising:

[0012] A collection module, used for collecting in real time a data group to be processed during the operation of the target boiler; wherein the data group to be processed includes at least one real-time input data and real-time output data corresponding to a data collection moment;

[0013] A prediction module is used to perform prediction processing on the real-time input data at each data collection moment based on a pre-built target prediction model to obtain prediction output data corresponding to each data collection moment;

[0014] A target residual determination module, used to determine the target residual corresponding to the to-be-processed data group according to the real-time output data and the predicted output data corresponding to each of the data collection moments;

[0015] An operating state determination module is used to determine the operating state of the target boiler according to the target residual and the target comparison threshold interval corresponding to the target residual.

[0016] In a third aspect, an embodiment of the present invention further provides an electronic device, including:

[0017] at least one processor; and

[0018] a memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent monitoring method for the boiler status described in any embodiment of the present invention.

[0020] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the intelligent monitoring method of the boiler status described in any embodiment of the present invention when executed.

[0021] In a fifth aspect, an embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the intelligent monitoring method for the boiler status as described in any one of the embodiments of the present invention.

[0022] The technical solution of the embodiment of the present invention is to collect a data group to be processed during the operation of the target boiler in real time; based on the pre-built target prediction model, the real-time input data at each data collection moment is predicted and processed to obtain the predicted output data corresponding to each data collection moment; according to the real-time output data and the predicted output data corresponding to each data collection moment, the target residual corresponding to the data group to be processed is determined; according to the target residual and the target comparison threshold interval corresponding to the target residual, the operation state of the target boiler is determined. In this technical solution, a data group to be processed during the operation of the target boiler is collected in real time, wherein the data group to be processed includes real-time input data and real-time output data corresponding to at least one data collection moment, and the real-time input data at each data collection moment in the data group to be processed is predicted and processed based on the pre-built target prediction model, to obtain the predicted output data at the corresponding data collection moment. Further, the residual at the corresponding data collection moment is determined according to the real-time output data and the predicted output data at each data collection moment, so as to determine the target residual corresponding to the data group to be processed, and then determine whether the operation state of the target boiler is abnormal based on whether the target residual belongs to the preset target comparison threshold interval. The invention solves the problems of inaccurate detection results and untimely detection of abnormal conditions of the boiler when the operating status of the boiler is detected based on manual experience or rules in the prior art, and realizes automated abnormal detection of the operating status of the boiler to improve detection efficiency and accuracy, and timely discover the abnormal operating status of the boiler.

[0023] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a flow chart of an intelligent monitoring method based on boiler status provided according to Embodiment 1 of the present invention;

[0026] Figure 2 is a flow chart of an intelligent monitoring method for boiler status provided according to Embodiment 2 of the present invention;

[0027] Figure 3 is a structural schematic diagram of an intelligent monitoring device for boiler status provided according to Embodiment 3 of the present invention;

[0028] Figure 4 It is a schematic diagram of the structure of an electronic device corresponding to the intelligent monitoring of the boiler status for implementing the embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only an embodiment of a part of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention. The acquisition, transmission, storage, use, and processing of data in the technical scheme of this application are in compliance with the relevant provisions of national laws and regulations. It should be noted that in the embodiments of this application, certain software, components, or models that already exist in the industry may be mentioned. They should be considered as exemplary. Their purpose is only to illustrate the feasibility of the implementation of the technical scheme of this application, but it does not mean that the applicant has or will necessarily use the scheme.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0031] Embodiment 1

[0032] Figure 1 A flow chart of a boiler intelligent state monitoring and abnormal warning system is provided for the first embodiment of the present invention. This embodiment can be applied to the case where at least one group of data groups to be processed is collected during the operation of the boiler, and the operating state of the boiler is automatically detected for abnormalities according to the maximum residual in each data group to be processed and a preset target comparison threshold interval. The method can be executed by an intelligent monitoring device for the boiler state. The intelligent monitoring device for the boiler state can be implemented in the form of hardware and / or software. The intelligent monitoring device for the boiler state can be configured in a computing device that can execute the intelligent monitoring method for the boiler state.

[0033] like Figure 1 As shown, the method includes:

[0034] S110, collecting in real time a data group to be processed during the operation of the target boiler.

[0035] The target boiler refers to a steam boiler heated by gas combustion, which is an important production equipment in industrial production. Its normal operation is crucial to ensuring production safety and efficiency. For example, the target boiler can be a vertical superheated steam boiler. The data group to be processed includes real-time input data and real-time output data corresponding to at least one data collection moment.

[0036] Exemplarily, during the operation of the target boiler, the operation data of the target boiler is collected in real time to obtain real-time input data and real-time output data corresponding to at least one data collection moment. The real-time input data may be natural gas consumption and water supply of the target boiler, and the real-time output data may be steam load, steam temperature and steam pressure of the target boiler.

[0037] It should be noted that the target boiler is affected by many factors during operation. Therefore, the real-time output data may also include the flue gas emission data of the target boiler, such as oxygen emissions, nitrogen oxide emissions, sulfur dioxide emissions, smoke dust emissions, flue gas flow rate, flue gas temperature, flue gas humidity and flue gas pressure, etc., so as to comprehensively consider the impact of the real-time input data and real-time output data of the target boiler according to the output parameters under various influencing factors, so as to obtain more accurate boiler operation data when collecting the real-time input data and real-time output data of the target boiler.

[0038] Optionally, before real-time collection of the data group to be processed during the operation of the target boiler, it also includes: obtaining a historical data group of the target boiler; inputting historical input data of the historical data group into a pre-built target prediction model to obtain historical predicted output data at each historical collection moment; based on the historical actual output data and historical predicted output data corresponding to each historical collection moment, determining a comparison threshold interval to be used corresponding to the target residual.

[0039] The historical data group includes historical input data and historical actual output data corresponding to at least one historical collection moment. The target prediction model refers to a model that can be used to predict the real-time output data corresponding to the corresponding data collection moment based on the real-time input data of the target boiler at at least one data collection moment. For example, the target prediction model can be a multidimensional time series prediction model. The historical actual output data refers to the actual output data corresponding to the historical input data at each historical collection moment. The historical predicted output data refers to the output data corresponding to each historical collection moment obtained by predicting the historical input data at each historical collection moment based on the target prediction model.

[0040] For example, for one of the historical collection moments, the historical input data A1 of the target boiler at the historical collection moment and the historical actual output data A2 of the target boiler at the historical collection moment are obtained according to the historical operation information of the target boiler, and the historical input data A1 is input into the target prediction model to obtain the historical prediction data A3 corresponding to the historical collection moment. The historical actual output data A2 and the historical prediction output data A3 may be the same or different.

[0041] In practical applications, before predicting the real-time input data of the target boiler based on the target prediction model, the target prediction model needs to be trained first to adjust the model parameters of the target prediction model to ensure the accuracy of the target prediction model's prediction of the real-time input data in the subsequent model application stage.

[0042] It should be noted that, since the operation of the target boiler is continuous, historical input data at multiple historical collection moments are usually taken as a historical data group, and the historical data group is input into the target prediction model to obtain historical prediction output data corresponding to each historical collection moment.

[0043] Based on this, for each historical collection moment corresponding to the historical actual output data and historical predicted output data, the corresponding residual data corresponding to the historical difference set moment can be obtained, and the target residual refers to the maximum residual data among the residual data corresponding to each historical collection moment in the historical data group.

[0044] On this basis, the technical solution mainly obtains the corresponding residuals based on the real-time output data and predicted output data at each data collection moment in the data group to be processed, so as to determine whether the operating state of the target boiler is abnormal according to whether the maximum residual in the data group to be processed exceeds the preset threshold. Therefore, in the training stage of the target prediction model, it is necessary to pre-set the comparison threshold interval to be used for detecting the maximum residual of the data group to be processed. Among them, the comparison threshold interval to be used includes the maximum comparison threshold and the minimum comparison threshold.

[0045] In the present technical solution, based on the historical actual output data and the historical predicted output data corresponding to each historical collection moment, a comparison threshold interval to be used corresponding to the target residual is determined, including: for each historical collection moment, based on the historical actual output data and the historical predicted output data of the current historical collection moment, the historical residual is obtained; the maximum residual of at least one historical residual is used as the target historical residual of the historical data group, and the target standard deviation corresponding to the target historical residual is determined; based on the target historical residual and the target standard deviation, the comparison threshold interval to be used is determined.

[0046] The historical residual refers to the residual data of the historical actual output data and the historical predicted output data corresponding to the same historical collection time. The target historical residual is the maximum historical residual corresponding to each historical collection time in the historical data group. The target standard deviation refers to the standard deviation corresponding to the historical collection time corresponding to the target historical residual, and the target standard deviation is also obtained based on the historical actual output data and the historical predicted output data at the historical collection time corresponding to the target historical residual.

[0047] Exemplarily, the historical data group includes 100 historical collection moments. According to the historical actual output data and historical predicted output data corresponding to each historical collection moment, the historical standard residual corresponding to the corresponding historical collection moment can be obtained, and all historical residuals are compared, and the largest historical residual is used as the target historical residual. On this basis, the target standard deviation corresponding to the historical collection moment is calculated according to the historical actual output data and historical predicted output data corresponding to the historical collection moment corresponding to the target historical residual, so as to determine the comparison threshold interval to be used for abnormal detection of the operating state of the target boiler based on the target historical residual and the target standard deviation. For example, if the historical collection moment corresponding to the target historical residual is the 30th historical collection moment, the standard deviation is calculated according to the historical actual output data and historical predicted output data corresponding to the 30th historical collection moment, and the standard deviation is used as the target standard deviation.

[0048] On this basis, based on the target historical residuals and the target standard deviation, the comparison threshold range to be used is determined, including: obtaining the value to be used based on the product of the preset multiple and the target standard deviation; obtaining the maximum comparison threshold based on the sum of the target historical residuals and the value to be used; and obtaining the minimum comparison threshold based on the difference between the target historical residuals and the value to be used.

[0049] Exemplarily, the target historical residual corresponding to the historical data set is N, the target standard deviation is M, and the preset multiple is set to 3, then the value to be used is 3M. ​​Further, based on the value to be used and the target historical residual, the maximum comparison threshold can be obtained as N+3M, and the minimum comparison threshold is N-3M, that is, the comparison threshold interval to be used can be expressed as [N-3M, N+3M].

[0050] S120: Based on the pre-built target prediction model, the real-time input data at each data collection moment is predicted and processed to obtain the predicted output data corresponding to each data collection moment.

[0051] Based on the above example, after training the target prediction model based on the data in the historical data group, the model parameters are adjusted so that in actual use, the real-time input data in the processing data group can be predicted based on the pre-built target prediction model to obtain the predicted output data corresponding to each data collection moment.

[0052] S130. Determine the target residual corresponding to the data group to be processed according to the real-time output data and the predicted output data corresponding to each data collection moment.

[0053] The target residual refers to the maximum residual among the residuals corresponding to each data collection moment in the data group to be processed.

[0054] In the present technical solution, similar to the historical residuals, after the data group to be processed is input into the target prediction model, the predicted output data corresponding to each data collection moment can be obtained, and based on the real-time output data and the predicted output data corresponding to the same data collection moment, the residuals of the corresponding data collection moment can be obtained, and the largest residual is used as the target residual of the data group to be processed.

[0055] S140. Determine the operating state of the target boiler according to the target residual and the target comparison threshold interval corresponding to the target residual.

[0056] The target comparison threshold interval refers to the threshold comparison interval for performing anomaly detection on the target residual of the data group to be processed.

[0057] In the present technical solution, the target comparison threshold interval corresponding to the data group to be processed is related to the array order of the data group to be processed. If the data group to be processed is the first data group to be processed, the threshold comparison interval to be used determined based on the historical data group is directly used as the target comparison threshold interval of the data group to be processed; if the data group to be processed is not the first data group to be processed, the target comparison threshold interval is determined based on the target residual in the data group to be processed and the standard deviation corresponding to the target residual.

[0058] On this basis, it is determined whether the operating state of the target boiler is abnormal according to the target residual and the target comparison threshold interval. For example, if the target residual is greater than the maximum comparison threshold in the target comparison threshold interval, or the target residual is less than the minimum comparison threshold in the target comparison threshold interval, it is determined that the operating state of the target boiler is abnormal.

[0059] The technical solution of the embodiment of the present invention is to collect a data group to be processed during the operation of the target boiler in real time; based on the pre-built target prediction model, the real-time input data at each data collection moment is predicted and processed to obtain the predicted output data corresponding to each data collection moment; according to the real-time output data and the predicted output data corresponding to each data collection moment, the target residual corresponding to the data group to be processed is determined; according to the target residual and the target comparison threshold interval corresponding to the target residual, the operation state of the target boiler is determined. In this technical solution, a data group to be processed during the operation of the target boiler is collected in real time, wherein the data group to be processed includes real-time input data and real-time output data corresponding to at least one data collection moment, and the real-time input data at each data collection moment in the data group to be processed is predicted and processed based on the pre-built target prediction model, to obtain the predicted output data at the corresponding data collection moment. Further, the residual at the corresponding data collection moment is determined according to the real-time output data and the predicted output data at each data collection moment, so as to determine the target residual corresponding to the data group to be processed, and then determine whether the operation state of the target boiler is abnormal based on whether the target residual belongs to the preset target comparison threshold interval. The invention solves the problems of inaccurate detection results and untimely detection of abnormal conditions of the boiler when the operating status of the boiler is detected based on manual experience or rules in the prior art, and realizes automated abnormal detection of the operating status of the boiler to improve detection efficiency and accuracy, and timely discover the abnormal operating status of the boiler.

[0060] Embodiment 2

[0061] Figure 2 A flowchart of an intelligent monitoring method for boiler status provided in Embodiment 2 of the present invention, optionally, the operating status of the target boiler is determined to be refined based on the target residual and the target comparison threshold interval corresponding to the target residual.

[0062] like Figure 2 As shown, the method includes:

[0063] S210, collecting the data group to be processed during the operation of the target boiler in real time.

[0064] S220: Based on the pre-built target prediction model, the real-time input data at each data collection moment is predicted and processed to obtain the predicted output data corresponding to each data collection moment.

[0065] S230: Determine the target residual corresponding to the data group to be processed according to the real-time output data and the predicted output data corresponding to each data collection moment.

[0066] S240 . Determine a target comparison threshold interval corresponding to the data group to be processed according to a data group sequence corresponding to the data group to be processed.

[0067] In practical applications, the operation status detection is usually carried out in real time based on the real-time operation data of the target boiler. Since the operation of the target boiler has a certain continuity, it is impossible to accurately determine whether the target boiler is operating normally based on the real-time operation data at a single data collection moment. Therefore, the data group to be processed in the technical solution usually includes real-time operation data at multiple consecutive data collection moments. For example, the real-time operation data at 60 data collection moments is used as a data group to be processed, and data detection is performed on each data group to be processed to determine the operation status of the target boiler according to the detection results.

[0068] It should be noted that when performing data detection on the data group to be processed, optionally, according to the data group order corresponding to the data group to be processed, a target comparison threshold interval corresponding to the target residual is determined, including: if the data group to be processed is the first data group to be processed, then the target comparison threshold interval is determined directly based on the target historical residual and the target standard deviation.

[0069] For example, in the process of real-time detection of the operating status of the target boiler, 10 data groups to be processed are collected as an example, wherein the first data group to be processed is the first data group to be processed, and all data groups to be processed except the first data group to be processed are not the first data group to be processed.

[0070] For the first data group to be processed, when determining the target comparison threshold interval, the threshold comparison interval for abnormality detection of the data group to be processed can be directly determined based on the target historical residual and target standard deviation determined in the historical data group. Specifically, the comparison threshold interval to be used determined based on the historical data group can be directly used as the target comparison threshold interval corresponding to the data group to be processed.

[0071] Optionally, according to the data group order corresponding to the data group to be processed, the target comparison threshold interval corresponding to the data group to be processed is determined, including: if the data group to be processed is not the first data group to be processed, then the residual to be compared in the data group to be processed is determined; if the residual to be compared is larger than the target historical residual, then based on the residual to be compared and the standard deviation corresponding to the residual to be compared, the target comparison threshold interval corresponding to the data group to be processed is determined; if the residual to be compared is smaller than the target historical residual, the target comparison threshold interval is determined based on the target historical residual and the target standard deviation.

[0072] The residual to be compared refers to the maximum residual among the residuals corresponding to the data collection moments in the non-first data group to be processed. It should be noted that the residual to be compared is used to distinguish and explain the maximum residual in the first data group to be processed and the non-first data group to be processed, that is, the residual to be compared corresponding to the non-first data group to be processed can also be called the target residual of the data group to be processed.

[0073] Specifically, if the residual to be compared is greater than the target historical residual corresponding to the historical data group, the standard deviation corresponding to the corresponding data collection time is calculated based on the real-time output data and predicted output data associated with the data collection time corresponding to the residual to be compared, and the standard deviation is used as the standard deviation corresponding to the residual to be compared. On this basis, the target comparison threshold interval corresponding to the data group to be processed is determined based on the residual to be compared and the corresponding standard deviation.

[0074] For example, the value to be updated is obtained based on the product of the preset multiple and the standard deviation to be compared; the maximum comparison threshold of the target comparison threshold interval is obtained based on the sum of the residual to be compared and the value to be updated, and the minimum comparison threshold of the target comparison threshold interval is obtained based on the difference between the residual to be compared and the value to be updated.

[0075] The advantage of this setting is that the comparison threshold interval to be used determined based on the historical data group is updated based on the target residual corresponding to the data group to be processed obtained in real time, and then the data in the subsequently collected data group to be processed is always detected for anomalies based on the first comparison threshold interval, thereby ensuring the accuracy of the detection results of the operating status of the target boiler.

[0076] S250: Determine the operating state of the target boiler according to the target residual and the target comparison threshold interval.

[0077] On this basis, if the target residual is greater than the maximum value of the target comparison threshold interval, or the target residual is less than the minimum value of the target comparison threshold interval, then the operating state of the target boiler is determined to be abnormal; if the target residual is less than the maximum value of the target comparison threshold interval, and the target residual is greater than the minimum value of the target comparison threshold interval, then the operating state of the target boiler is determined to be normal.

[0078] In addition, in the present technical solution, when determining the operating state of the target boiler based on the target residual, a judgment can also be made based on the first-order difference of the target residual. Specifically, the first-order difference corresponding to the target residual is determined; if the first-order difference exceeds a preset ratio of the threshold interval of the target comparison threshold, it is determined that there is abnormal data in the data group to be processed, and the operating state of the target boiler is determined to be an abnormal state.

[0079] For example, the preset ratio is set to 10%. If the first-order difference corresponding to the target residual exceeds 10% of the maximum comparison threshold of the target comparison threshold interval, or is less than 10% of the minimum comparison threshold of the target comparison threshold interval, it is determined that there is abnormal data in the data group to be processed. At this time, it can be determined that the operating state of the target boiler is abnormal.

[0080] The technical solution of the embodiment of the present invention determines the target comparison threshold interval corresponding to the data group to be processed according to the data group order corresponding to the data group to be processed; if the target residual is greater than the maximum value of the target comparison threshold interval, or the target residual is less than the minimum value of the target comparison threshold interval, then the operating state of the target boiler is determined to be an abnormal state; if the target residual is less than the maximum value of the target comparison threshold interval, and the target residual is greater than the minimum value of the target comparison threshold interval, then the operating state of the target boiler is determined to be a normal state. In this technical solution, the target comparison threshold interval corresponding to the corresponding data group to be processed is determined according to the difference in data group data of the data group to be processed, and the target comparison threshold interval is updated in real time with the boiler operation data in the collected data group to be processed, so as to ensure that the target comparison threshold interval used in the abnormality detection process is always the latest threshold comparison interval, so that the data in each data group to be processed can be more accurately detected for abnormalities. The invention solves the problems of inaccurate detection results and untimely detection of abnormal conditions of the boiler when the operating status of the boiler is detected based on manual experience or rules in the prior art, and realizes automated abnormal detection of the operating status of the boiler to improve detection efficiency and accuracy, and timely discover the abnormal operating status of the boiler.

[0081] Embodiment 3

[0082] Figure 3 This is a schematic diagram of the structure of an intelligent monitoring device for boiler status provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes: a collection module 310, a prediction module 320, a target residual determination module 330 and an operation status determination module 340.

[0083] The acquisition module 310 is used to acquire the data group to be processed in real time during the operation of the target boiler; wherein the data group to be processed includes at least one real-time input data and real-time output data corresponding to a data acquisition moment;

[0084] The prediction module 320 is used to perform prediction processing on the real-time input data at each data collection moment based on the pre-built target prediction model to obtain the prediction output data corresponding to each data collection moment;

[0085] A target residual determination module 330 is used to determine the target residual corresponding to the data group to be processed according to the real-time output data and the predicted output data corresponding to each data collection moment;

[0086] The operating state determination module 340 is used to determine the operating state of the target boiler according to the target residual and the target comparison threshold interval corresponding to the target residual.

[0087] The technical solution of the embodiment of the present invention is to collect a data group to be processed during the operation of the target boiler in real time; based on the pre-built target prediction model, the real-time input data at each data collection moment is predicted and processed to obtain the predicted output data corresponding to each data collection moment; according to the real-time output data and the predicted output data corresponding to each data collection moment, the target residual corresponding to the data group to be processed is determined; according to the target residual and the target comparison threshold interval corresponding to the target residual, the operation state of the target boiler is determined. In this technical solution, a data group to be processed during the operation of the target boiler is collected in real time, wherein the data group to be processed includes real-time input data and real-time output data corresponding to at least one data collection moment, and the real-time input data at each data collection moment in the data group to be processed is predicted and processed based on the pre-built target prediction model, to obtain the predicted output data at the corresponding data collection moment. Further, the residual at the corresponding data collection moment is determined according to the real-time output data and the predicted output data at each data collection moment, so as to determine the target residual corresponding to the data group to be processed, and then determine whether the operation state of the target boiler is abnormal based on whether the target residual belongs to the preset target comparison threshold interval. The invention solves the problems of inaccurate detection results and untimely detection of abnormal conditions of the boiler when the operating status of the boiler is detected based on manual experience or rules in the prior art, and realizes automated abnormal detection of the operating status of the boiler to improve detection efficiency and accuracy, and timely discover the abnormal operating status of the boiler.

[0088] Optionally, the intelligent monitoring device for boiler status further includes: a historical data group acquisition module, used to acquire a historical data group of the target boiler; wherein the historical data group includes historical input data and historical actual output data corresponding to at least one historical collection moment;

[0089] A historical prediction output data determination module is used to input the historical input data of the historical data group into a pre-built target prediction model to obtain the historical prediction output data corresponding to each historical collection moment;

[0090] The target comparison threshold interval determination module is used to determine the comparison threshold interval to be used corresponding to the target residual based on the historical actual output data and the historical predicted output data corresponding to each historical collection moment.

[0091] Optionally, the comparison threshold interval determination module to be used includes: a historical residual determination unit, which is used to obtain the historical residual based on the historical actual output data and the historical predicted output data at the current historical collection moment for each historical collection moment;

[0092] a standard deviation determination unit, configured to use a maximum residual among at least one historical residual as a target historical residual of the historical data group, and determine a target standard deviation corresponding to the target historical residual;

[0093] The target comparison threshold interval determination unit is used to determine the comparison threshold interval to be used based on the target historical residual and the target standard deviation.

[0094] Optionally, the comparison threshold interval determination unit to be used includes: a value determination subunit to be used, which is used for the comparison threshold interval to be used to include a maximum comparison threshold and a minimum comparison threshold, and obtains the value to be used according to the product of a preset multiple and a target standard deviation;

[0095] The threshold determination subunit is used to obtain a maximum comparison threshold based on the sum of the target historical residual and the value to be used; and to obtain a minimum comparison threshold based on the difference between the target historical residual and the value to be used.

[0096] Optionally, the operation status determination module includes: an interval determination unit, for determining a target comparison threshold interval corresponding to the data group to be processed according to a data group sequence corresponding to the data group to be processed;

[0097] an abnormal state determination unit, for determining that the operating state of the target boiler is an abnormal state if the target residual is greater than a maximum value of the target comparison threshold interval, or the target residual is less than a minimum value of the target comparison threshold interval;

[0098] The normal state determination unit is used to determine that the operating state of the target boiler is a normal state if the target residual is less than the maximum value of the target comparison threshold interval and the target residual is greater than the minimum value of the target comparison threshold interval.

[0099] Optionally, the operation status determination module includes: a residual to be compared determination unit, configured to determine the residual to be compared in the data group to be processed if the data group to be processed is not the first data group to be processed;

[0100] A first threshold interval determination unit is used to determine a target comparison threshold interval corresponding to the data group to be processed based on the residual to be compared and the standard deviation corresponding to the residual to be compared if the residual to be compared is greater than the target historical residual;

[0101] The second threshold interval determination unit is used to determine a target comparison threshold interval based on the target historical residual and the target standard deviation if the residual to be compared is less than the target historical residual.

[0102] Optionally, the operating status determination module includes: a third threshold interval determination unit, used to determine the target comparison threshold interval directly based on the target historical residual and the target standard deviation if the data group to be processed is the first data group to be processed.

[0103] Optionally, the intelligent monitoring device for boiler status further includes: a first-order difference determination module, used to determine a first-order difference corresponding to the target residual;

[0104] The differential comparison module is used to determine that there is abnormal data in the data group to be processed and determine that the operating state of the target boiler is abnormal if the first-order difference exceeds a preset proportion of the threshold interval of the target comparison threshold.

[0105] The intelligent monitoring device for boiler status provided in the embodiment of the present invention can execute the intelligent monitoring method for boiler status provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0106] Embodiment 4

[0107] Figure 4 The structural schematic diagram of the electronic device 10 of the boiler intelligent state monitoring and abnormal warning system of an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0108] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0109] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0110] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the intelligent monitoring method of the boiler status.

[0111] In some embodiments, the intelligent monitoring method of the boiler state can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the intelligent monitoring method of the boiler state described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the intelligent monitoring method of the boiler state in any other appropriate manner (for example, by means of firmware).

[0112] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0113] The computer program for implementing the intelligent monitoring method of the boiler state of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0114] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0115] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0116] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0117] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0118] Embodiment 5

[0119] An embodiment of the present invention further provides a computer program product corresponding to the intelligent monitoring method for boiler status, including a computer program, which, when executed by a processor, implements the intelligent monitoring method for boiler status provided in any embodiment of the present application.

[0120] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0121] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0122] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent monitoring method for boiler status, characterized in that: include: Collecting in real time a data group to be processed during the operation of the target boiler; wherein the data group to be processed includes at least one real-time input data and real-time output data corresponding to a data collection moment; Based on the pre-built target prediction model, the real-time input data at each data collection moment is predicted and processed to obtain the predicted output data corresponding to each data collection moment; Determining the target residual corresponding to the data group to be processed according to the real-time output data and the predicted output data corresponding to each of the data collection moments; The operating state of the target boiler is determined according to the target residual and the target comparison threshold interval corresponding to the target residual.

2. The method according to claim 1, characterized in that Before the real-time collection of the data group to be processed during the operation of the target boiler, the method further includes: Acquire a historical data group of the target boiler; wherein the historical data group includes historical input data and historical actual output data corresponding to at least one historical collection moment; Inputting the historical input data of the historical data group into a pre-built target prediction model to obtain historical prediction output data corresponding to each historical collection moment; Based on the historical actual output data and the historical predicted output data corresponding to each of the historical collection moments, a comparison threshold interval to be used corresponding to the target residual is determined.

3. The method according to claim 2, characterized in that The determining, based on the historical actual output data and the historical predicted output data corresponding to each of the historical collection moments, a comparison threshold interval to be used corresponding to the target residual includes: For each of the historical collection moments, based on the historical actual output data and the historical predicted output data at the current historical collection moment, a historical residual is obtained; Taking the maximum residual of at least one historical residual as the target historical residual of the historical data group, and determining a target standard deviation corresponding to the target historical residual; Based on the target historical residual and the target standard deviation, a comparison threshold interval to be used is determined.

4. The method according to claim 3, characterized in that The comparison threshold interval to be used includes a maximum comparison threshold and a minimum comparison threshold, and the determining of the comparison threshold interval to be used based on the target historical residual and the target standard deviation includes: Obtaining a value to be used according to the product of a preset multiple and the target standard deviation; The maximum comparison threshold is obtained based on the sum of the target historical residual and the value to be used; and the minimum comparison threshold is obtained based on the difference between the target historical residual and the value to be used.

5. The method according to claim 1, characterized in that The step of determining the operating state of the target boiler according to the target residual and a target comparison threshold interval corresponding to the target residual includes: Determining a target comparison threshold interval corresponding to the data group to be processed according to a data group sequence corresponding to the data group to be processed; If the target residual is greater than the maximum value of the target comparison threshold interval, or the target residual is less than the minimum value of the target comparison threshold interval, then determining that the operating state of the target boiler is an abnormal state; If the target residual is smaller than the maximum value of the target comparison threshold interval, and the target residual is larger than the minimum value of the target comparison threshold interval, it is determined that the operating state of the target boiler is a normal state.

6. The method according to claim 3, characterized in that The step of determining a target comparison threshold interval corresponding to the data group to be processed according to the data group sequence corresponding to the data group to be processed includes: If the data group to be processed is not the first data group to be processed, determining the residual to be compared in the data group to be processed; If the residual to be compared is greater than the target historical residual, determining a target comparison threshold interval corresponding to the data group to be processed based on the residual to be compared and a standard deviation corresponding to the residual to be compared; If the residual to be compared is smaller than the target historical residual, the target comparison threshold interval will be determined based on the target historical residual and the target standard deviation.

7. The method according to claim 3, characterized in that The step of determining a target comparison threshold interval corresponding to the target residual according to a data group sequence corresponding to the data group to be processed includes: If the data group to be processed is the first data group to be processed, the target comparison threshold interval is determined directly based on the target historical residual and the target standard deviation.

8. The method according to claim 1, characterized in that Also includes: determining a first-order difference corresponding to the target residual; If the first-order difference exceeds a preset ratio of the threshold interval of the target comparison threshold, it is determined that abnormal data exists in the data group to be processed, and the operating state of the target boiler is determined to be an abnormal state.

9. An intelligent monitoring device for boiler status, characterized in that: include: A collection module, used for collecting in real time a data group to be processed during the operation of the target boiler; wherein the data group to be processed includes at least one real-time input data and real-time output data corresponding to a data collection moment; A prediction module is used to perform prediction processing on the real-time input data at each data collection moment based on a pre-built target prediction model to obtain prediction output data corresponding to each data collection moment; A target residual determination module, used to determine the target residual corresponding to the to-be-processed data group according to the real-time output data and the predicted output data corresponding to each of the data collection moments; An operating state determination module is used to determine the operating state of the target boiler according to the target residual and the target comparison threshold interval corresponding to the target residual.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent monitoring method for the boiler state according to any one of claims 1 to 8.

Images