Gas data anomaly detection method, device, equipment, medium and program product

Abstract

The present invention discloses a gas data anomaly detection method, apparatus, device, medium, and program product, relating to the field of data detection technology. By obtaining a percentage value of a first gas component content and a percentage value of a second gas component content containing the same component element, an anomaly detection is performed on the percentage value of the first gas component content to obtain a first gas component content detection result; an anomaly detection is performed on the percentage value of the second gas component content to obtain a second gas component content detection result, and an anomaly detection result of the gas detection data is determined based on the first gas component content detection result and the second gas component content detection result. Embodiments of the present invention can improve the accuracy of gas data anomaly detection.

Description

Technical Field

[0001] The present invention relates to the field of data detection technology, and in particular to a gas data anomaly detection method, device, equipment medium and program product. Background Art

[0002] With the rapid development of industrialization and urbanization, different industries have different gas emission requirements. Inappropriate gas emissions will have an impact on the climate and ecology. Therefore, it is necessary to monitor gas emission data.

[0003] In the existing technology, when detecting anomalies in gas data of a certain type in the exhaust gas, the data of this type of gas is generally only detected using a preset concentration threshold, and the detected gas data of this type, such as gas concentration, is used to determine whether the detected gas data has an anomaly.

[0004] In the process of realizing the present invention, the inventors discovered that the existing technology has the following defects: the monitoring system in the existing technology only uses a single concentration threshold detection method to detect the concentration of a certain type of gas. When the equipment used to detect the gas concentration itself has problems, it is impossible to effectively identify the abnormal gas concentration caused by the equipment failure. In a specific example, after the coal-fired power plant is started, the CO2 concentration will fluctuate between 8% and 18% according to the boiler load. Assuming that the actual true value of the CO2 concentration is 16%, but at this time the instrument has an abnormality, resulting in the CO2 concentration detected by the equipment being only 12%, it is difficult to identify whether the CO2 concentration data is abnormal by setting a unified threshold. Summary of the Invention

[0005] The present invention provides a gas data anomaly detection method, device, equipment, medium and program product, which can improve the accuracy of gas data anomaly detection.

[0006] According to one aspect of the present invention, a method for detecting anomalies in gas data is provided, comprising:

[0007] Obtaining a percentage value of a first gas component content and a percentage value of a second gas component content in gas detection data output by a gas detection device;

[0008] Performing an abnormality detection on the percentage value of the first gas component content to obtain a first gas component content detection result;

[0009] Performing an abnormality detection on the percentage value of the second gas component content to obtain a second gas component content detection result;

[0010] determining an abnormality detection result of the gas detection data according to the first gas component content detection result and the second gas component content detection result;

[0011] The first gas component and the second gas component in the gas detection data include the same component elements.

[0012] According to another aspect of the present invention, there is provided a gas data anomaly detection device, comprising:

[0013] A data acquisition module, configured to acquire a percentage value of a first gas component content and a percentage value of a second gas component content in gas detection data output by a gas detection device;

[0014] a first gas detection module, configured to perform abnormality detection on a percentage value of the first gas component content to obtain a first gas component content detection result;

[0015] a second gas detection module, configured to perform abnormality detection on the percentage value of the second gas component content to obtain a second gas component content detection result;

[0016] a data anomaly detection module, configured to determine an anomaly detection result of the gas detection data based on the first gas component content detection result and the second gas component content detection result;

[0017] The first gas component and the second gas component in the gas detection data include the same component elements.

[0018] According to another aspect of the present invention, there is provided a programmable logic controller, the programmable logic controller comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can perform any one of the gas data anomaly detection methods.

[0022] According to another aspect of the present invention, a readable storage medium is provided, wherein the readable storage medium stores control instructions, and the control instructions are used to enable a processor to implement any one of the gas data anomaly detection methods when executed.

[0023] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the gas data anomaly detection method according to any embodiment of the present invention.

[0024] The technical solution of the embodiment of the present invention obtains the percentage value of the first gas component content and the percentage value of the second gas component content in the gas detection data output by the gas detection device, and performs an abnormality detection on the percentage value of the first gas component content to obtain the first gas component content detection result; and performs an abnormality detection on the percentage value of the second gas component content to obtain the second gas component content detection result. Finally, the abnormal detection result of the gas detection data is determined based on the first gas component content detection result and the second gas component content detection result. Since the first gas component and the second gas component in the gas detection data include the same component elements, the above technical solution can consider the intrinsic connection between the first gas and the second gas when detecting the abnormal detection result of the gas detection data, thereby realizing abnormal detection of the gas detection data, solving the problem of low detection accuracy in the prior art of performing gas detection based on the concentration threshold of only one type of gas data, and can improve the accuracy of abnormal detection of gas data.

[0025] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] 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.

[0027] Figure 1 This is a flow chart of gas data anomaly detection provided according to the first embodiment of the present invention;

[0028] Figure 2 Schematic diagram of an online flue gas carbon emission monitoring system for carbon emission detection in the prior art;

[0029] Figure 3 This is a flowchart of another gas data anomaly detection method provided in accordance with the second embodiment of the present invention;

[0030] Figure 4 2 is a schematic diagram of the structure of a gas data anomaly detection device provided according to a third embodiment of the present invention;

[0031] Figure 5 This is a structural diagram of an electronic device provided in Example 4 of the present invention. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the description 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. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] Example 1

[0035] Figure 1 A flow chart of a gas data anomaly detection method is provided for the first embodiment of the present invention. This embodiment is applicable to the case where gas anomaly detection is performed using different gas components containing the same component elements. The method can be performed by a gas data anomaly detection device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0036] S110 , obtaining a percentage value of a first gas component content and a percentage value of a second gas component content in gas detection data output by a gas detection device.

[0037] The first gas component and the second gas component in the gas detection data include the same component element. For example, the first gas component and the second gas component may be carbon dioxide and oxygen, both of which include the element oxygen. Alternatively, the first gas component and the second gas component may be nitric oxide and nitrogen, both of which include the element nitrogen.

[0038] The gas detection device may be a device used to detect information such as gas components and concentration values ​​of various gases in the emitted gas in various emission gas scenarios.

[0039] Among them, the gas detection data may include the first gas component and the second gas component and the corresponding component content, etc. The gas component content can be calculated by the concentration of the gas. The first gas component can be a gas type determined according to the gas detection requirements, for example, it can be carbon dioxide gas, carbon monoxide gas and other gases. The first gas component can be any gas type set by the user according to the gas detection requirements; the percentage value of the first gas component content can be the percentage of the first gas component content in the gas detection data. After obtaining the detection signals of various gases in the gas detection data, the detected first gas component signal can be sent to the controller, and the controller can convert the first gas component signal into the percentage value of the first gas component content corresponding to the first gas component. Among them, the percentage value of the first gas component content can be used to characterize the percentage value of the first gas component in the flue gas, such as 20%, 18%, etc.

[0040] The second gas component can be a gas containing the same element as the first gas component. For example, when the first gas component is carbon dioxide, the second gas component can be oxygen gas, which contains the same oxygen element as the first gas component, or another gas containing oxygen. When the first gas component is nitric oxide, the second gas component can be nitrogen gas, which contains the same nitrogen element as the first gas component, or another gas containing nitrogen. Similarly, the percentage value of the second gas component content can be the percentage of the second gas component content in the gas detection data. After obtaining the detection signals of various gases in the gas detection data, the detected second gas component signals can be sent to a controller, which can convert the second gas component signals into the percentage value of the second gas component content corresponding to the second gas. The percentage value of the second gas component content can be used to represent the percentage of the second gas component in the exhaust gas, for example, 5%, 7%, etc. It should be noted that the present invention does not limit the specific method for calculating the percentage values ​​of the first gas component content and the percentage values ​​of the second gas component content. Those skilled in the art can select a calculation method based on their experience.

[0041] It is understandable that the types of the first gas component and the second gas component may vary depending on the gas detection requirements. For example, when anomaly detection is required for carbon dioxide gas detection data, carbon dioxide gas may be used as the first gas component and oxygen gas may be used as the second gas component; when anomaly detection is required for nitric oxide gas detection data, nitric oxide gas may be used as the first gas component and nitrogen gas may be used as the second gas component.

[0042] Specifically, obtaining the percentage value of the first gas component content and the percentage value of the second gas component content in the gas detection data output by the gas detection device can be performed by obtaining the detection signals of the first gas component and the second gas component in the flue gas to be detected through the gas detection device, and then sending the detection signals of the first gas component and the second gas component to the controller, and the controller converts the detection signals of the first gas component and the second gas component into the percentage value of the first gas component content and the percentage value of the second gas component content according to a calculation method pre-selected by the user.

[0043] S120: Perform an abnormality detection on the percentage value of the first gas component content to obtain a first gas component content detection result.

[0044] The first gas component content detection result may be a detection result of whether the first gas component content data obtained after judging the percentage value of the detected first gas component content is abnormal.

[0045] In an optional embodiment of the present invention, performing abnormal detection on the percentage value of the first gas component content to obtain the first gas component content detection result may include: comparing the percentage value of the first gas component content with the attribution relationship of a preset first gas component threshold range to obtain the first gas component content detection result.

[0046] The first gas component threshold interval may be a numerical range used as a reference when initially detecting whether gas detection data is abnormal. This range may serve as a basis for determining whether the detection result of the first gas component is abnormal during the initial detection of gas detection data. For example, the first gas component threshold interval may be a range such as (0, 15%), [1%, 12%), or [5%, 20%).

[0047] For example, if the threshold interval of the first gas component is [5%, 20%], it means that if the percentage value of the first gas component content is greater than or equal to 5% and less than or equal to 20%, that is, the percentage value of the first gas component content is within the range of 5% to 20% or equal to 5% or 20%, then it means that when the gas detection data is first detected to see whether it is abnormal, the detection result of the first gas component is normal; if the percentage value of the first gas component content is less than 5% or greater than 20%, that is, the percentage value of the first gas component content is not within the range of 5% to 20% and is not equal to 5% or 20%, then it means that when the gas detection data is first detected to see whether it is abnormal, the detection result of the first gas component is abnormal.

[0048] S130: Perform an abnormality detection on the percentage value of the second gas component content to obtain a second gas component content detection result.

[0049] The second gas component content detection result may be a detection result of whether the second gas component content data is abnormal after judging the percentage value of the second gas component content detected by the second gas component threshold interval.

[0050] In an optional embodiment of the present invention, performing abnormal detection on the percentage value of the second gas component content to obtain the second gas component content detection result may include: determining whether the percentage value of the second gas component content is within a preset second gas component threshold range, and obtaining the second gas component content detection result based on the judgment result.

[0051] The second gas composition threshold interval can be a reference value range for the initial detection of whether the gas detection data is abnormal. This range can be used as a basis for determining whether the second gas composition detection result is abnormal during the initial detection of whether the gas detection data is abnormal. For example, the second gas composition threshold interval can be a range such as (1%, 20%), [0%, 18%), or [3%, 25%).

[0052] For example, if the second gas component threshold interval is [3%, 25%], it means that if the percentage value of the second gas component content is greater than or equal to 3% and less than or equal to 25%, that is, the percentage value of the second gas component content is in the range of 3% to 25% or equal to 3% or 25%, then it means that when the gas detection data is first detected to see if it is abnormal, the detection result of the second gas component is normal; if the percentage value of the second gas component content is less than 3% or greater than 25%, that is, the percentage value of the second gas component content is not in the range of 3% to 25% and is not equal to 3% or 25%, then it means that when the gas detection data is first detected to see if it is abnormal, the detection result of the second gas component is abnormal.

[0053] S140. Determine an abnormality detection result of the gas detection data based on the first gas component content detection result and the second gas component content detection result, wherein the first gas component and the second gas component in the gas detection data include the same component elements.

[0054] The abnormality detection result of the gas detection data may be a result of simultaneously performing gas abnormality detection on the first gas component and the second gas component in the gas detection data, and is used to indicate whether the gas detection data detected for the first time has abnormality.

[0055] Optionally, if the first gas component is a gas type that needs to be detected, the first gas component content detection result can be used as a primary basis, supplemented by the second gas component content detection result, to comprehensively determine whether the first gas component content is abnormal. If the second gas component is a gas type that needs to be detected, the second gas component content detection result can be used as a primary basis, supplemented by the first gas component content detection result, to comprehensively determine whether the second gas component content is abnormal.

[0056] Exemplarily, determining the abnormal detection result of the gas detection data based on the first gas component content detection result and the second gas component content detection result can be performed by first obtaining the first gas component content detection result based on whether the percentage value of the first gas component content is within the preset first gas component threshold value interval. If the percentage value of the first gas component content is not within the preset first gas component threshold value interval, it indicates that the detection result of the first gas detection data is abnormal. If the percentage value of the first gas component content is within the preset first gas component threshold value interval, then obtaining the second gas component content detection result based on whether the percentage value of the second gas component content is within the preset second gas component threshold value interval. If the percentage value of the second gas component content is not within the preset second gas component threshold value interval, it indicates that the detection result of the first gas detection data is abnormal. If the percentage value of the second gas component content is within the preset second gas component threshold value interval, it indicates that the detection result of the gas detection data is normal.

[0057] In a specific example, taking the carbon dioxide concentration detection as an example, in the prior art, when abnormal detection of carbon dioxide gas data detected by the detection instrument is performed, it can be achieved through the flue gas carbon emission online monitoring system. Figure 1 Schematic diagram of an online flue gas carbon emission monitoring system for carbon emission detection in the prior art, such as Figure 1 As shown in the figure, the flue gas carbon emission online monitoring system mainly consists of a flue gas sampling module, a pretreatment module, a concentration detection module, a data acquisition and operation control module, a data processing and statistics module, a database, a host computer and other parts.

[0058] Existing pilot gas monitoring systems set gas concentration thresholds in the "Data Collection and Operation Control Module" or "Data Processing and Statistics Module." Based on these thresholds, the collected carbon concentration is determined to be above the threshold. This then triggers an alarm to alert users of abnormal conditions. However, these systems are limited in the number of abnormalities they can identify. For example, after a coal-fired power plant is started up, the CO2 concentration fluctuates between 8% and 18% depending on boiler load. If the true value is 16%, but an instrument anomaly causes the CO2 concentration to be only 12%, it would be difficult to identify abnormal CO2 concentration data using a unified threshold.

[0059] To meet the needs of carbon dioxide concentration detection, existing technologies also widely use big data, machine learning, deep learning and other means to identify whether the current data is abnormal based on the predicted values ​​of complex models. This abnormality identification method can only be run in the "data processing and statistics module" of the host computer, but this method requires high computing power and cannot be integrated into the microcontroller or PLC (Programmable Logic Controller) in industrial scenarios.

[0060] Exemplarily, the technical solution of an embodiment of the present invention, when performing anomaly detection on carbon dioxide concentration data, can first obtain the percentage value of the carbon dioxide content in the flue gas, and then determine whether the percentage value of the carbon dioxide content is within the threshold range corresponding to carbon dioxide. If the percentage value of the carbon dioxide content is not within the threshold range corresponding to carbon dioxide, the detection result of the carbon dioxide concentration data can be directly determined to be abnormal. If the percentage value of the carbon dioxide content is within the threshold range corresponding to carbon dioxide, the percentage value of the oxygen content in the flue gas can be obtained, and then determine whether the percentage value of the oxygen content is within the threshold range corresponding to oxygen. If the percentage value of the oxygen content is not within the threshold range corresponding to oxygen, the detection result of the carbon dioxide concentration data can be determined to be abnormal. When performing anomaly detection on carbon dioxide concentration data, by mainly using the carbon dioxide content detection result and supplementing it with the oxygen content detection result to comprehensively determine whether the content of the first gas component is abnormal, the problem of the prior art in being unable to identify gas data anomalies within a common value range can be avoided, and the accuracy of gas data anomaly detection can be improved.

[0061] The technical solution of the embodiment of the present invention obtains the percentage value of the first gas component content and the percentage value of the second gas component content in the gas detection data output by the gas detection device, and performs an abnormality detection on the percentage value of the first gas component content to obtain the first gas component content detection result; and performs an abnormality detection on the percentage value of the second gas component content to obtain the second gas component content detection result. Finally, the abnormal detection result of the gas detection data is determined based on the first gas component content detection result and the second gas component content detection result. Since the first gas component and the second gas component in the gas detection data include the same component elements, the above technical solution can consider the intrinsic connection between the first gas and the second gas when detecting the abnormal detection result of the gas detection data, thereby realizing abnormal detection of the gas detection data, solving the problem of low detection accuracy in the prior art of performing gas detection based on the concentration threshold of only one type of gas data, and can improve the accuracy of abnormal detection of gas data.

[0062] Example 2

[0063] Figure 3 A flowchart of gas data anomaly detection is provided for the second embodiment of the present invention. Based on the above embodiment, this embodiment will determine the abnormal detection result of the gas detection data according to the first gas component content detection result and the second gas component content detection result. Specifically: when it is determined that the first gas component content detection result and / or the second gas component content detection result are both abnormal, the detection result of the gas detection data is determined to be abnormal; when it is determined that the first gas component content detection result and the second gas component content detection result are both normal, the gas detection data is subjected to a secondary detection based on the percentage value of the first gas component content and the percentage value of the second gas component content, and the abnormal detection result of the gas detection data is determined based on the secondary detection result. Figure 3 As shown, the method of this embodiment may include:

[0064] S210: Obtain a percentage value of a first gas component content and a percentage value of a second gas component content in gas detection data output by a gas detection device.

[0065] Optionally, before obtaining the percentage values ​​of the first gas component content and the percentage values ​​of the second gas component content in the gas detection data output by the gas detection device, it can also include: obtaining the gas component detection data obtained by the gas detection device continuously performing gas detection under a set working state; determining the preset first gas component threshold interval and the preset second gas component threshold interval based on the percentage values ​​of the first gas component content and the percentage values ​​of the second gas component content in the gas component detection data.

[0066] The set working state may be a certain working state of the gas detection device, for example, including but not limited to a full-load working state, a shutdown working state and a normal working state.

[0067] Optionally, obtaining gas composition detection data obtained by the gas detection device through continuous gas detection in a set working state may include: obtaining gas composition detection data obtained by the gas detection device through continuous gas detection when the machine is working at full load; obtaining gas composition detection data obtained by the gas detection device through continuous gas detection when the machine is stopped.

[0068] Specifically, a gas component detection signal obtained by the gas detection device during continuous gas detection under full-load operation is obtained, and component detection signals of the first gas component and the second gas component are extracted from the gas component detection data. The component detection signals of the first gas component and the second gas component are then transmitted to a controller. After receiving the component detection signals of the first gas component and the second gas component, the controller can convert the component detection signals of the first gas component and the second gas component into a percentage value of the first gas component content and a percentage value of the second gas component content corresponding to the first gas component and the second gas component.

[0069] Specifically, a gas component detection signal obtained by the gas detection device during continuous gas detection while the machine is in a stopped working state is obtained, and component detection signals of the first gas component and the second gas component are extracted from the gas component detection data. The component detection signals of the first gas component and the second gas component are then transmitted to a controller. After receiving the component detection signals of the first gas component and the second gas component, the controller can convert the component detection signals of the first gas component and the second gas component into a percentage value of the first gas component content and a percentage value of the second gas component content corresponding to the first gas component and the second gas component.

[0070] Specifically, determining the preset first gas composition threshold interval and the preset second gas composition threshold interval based on the percentage values ​​of the first gas composition content and the percentage values ​​of the second gas composition content in the gas composition detection data can be performed by obtaining the limit values ​​of the percentage values ​​of the first gas composition content and the percentage values ​​of the second gas composition content obtained when the machine is in a full-load working state and a shutdown working state, wherein the limit values ​​may include a maximum value and a minimum value, and then determining the obtained maximum value as the upper limit value of the preset first gas composition threshold interval and the preset second gas composition threshold interval, and determining the extracted minimum value as the lower limit value of the preset first gas composition threshold interval and the preset second gas composition threshold interval to complete the determination of the preset first gas composition threshold interval and the preset second gas composition threshold interval. It should be noted that the percentage value of the gas composition content obtained in the full-load working state is not necessarily the maximum value of the gas composition content percentage value, and the percentage value of the gas composition content obtained in the shutdown working state is not necessarily the minimum value of the gas composition content percentage value. The specific situation should be determined according to the specific working conditions.

[0071] S220: Perform an abnormality detection on the percentage value of the first gas component content to obtain a first gas component content detection result.

[0072] S230: Perform an abnormality detection on the percentage value of the second gas component content to obtain a second gas component content detection result.

[0073] S240: Determine whether the first gas component content detection result and / or the second gas component content detection result is abnormal. If so, execute step S250; if not, execute step S260.

[0074] Specifically, the first gas component content detection result is obtained based on whether the percentage value of the first gas component content is within the preset first gas component threshold interval. If the percentage value of the first gas component content is not within the preset first gas component threshold interval, the detection result of the gas detection data is determined to be abnormal; if the percentage value of the first gas component content is within the preset first gas component threshold interval, the second gas component content detection result can be further obtained based on whether the percentage value of the second gas component content is within the preset second gas component threshold interval. If the percentage value of the second gas component content is not within the preset second gas component threshold interval, the detection result of the gas detection data is determined to be abnormal. If the percentage value of the first gas component content is within the preset first gas component threshold interval and the percentage value of the second gas component content is also within the preset second gas component threshold interval, a secondary detection is required.

[0075] S250: Determine that the detection result of the gas detection data is abnormal.

[0076] Specifically, determining that the detection result of the gas detection data is abnormal can be that after obtaining the first gas component content detection result and the second gas component content detection result, if the percentage value of the first gas component content is not within the preset first gas component threshold interval and / or the percentage value of the second gas component content is within the preset second gas component threshold interval, then it indicates that the first gas component content detection result and / or the second gas component content detection result is a detection abnormality. At this time, it indicates that the first detection result of the gas detection data is abnormal.

[0077] S260 , performing secondary detection on the gas detection data according to the percentage value of the first gas component content and the percentage value of the second gas component content, and determining an abnormal detection result of the gas detection data according to the secondary detection result.

[0078] Specifically, when it is determined that the first gas component content detection result and the second gas component content detection result are both normal, the gas detection data can be further subjected to secondary detection based on the percentage value of the first gas component content and the percentage value of the second gas component content, and the abnormal detection result of the gas detection data can be determined based on the secondary detection result.

[0079] In an optional embodiment of the present invention, a secondary detection is performed on the gas detection data based on the percentage value of the first gas component content and the percentage value of the second gas component content, and an abnormal detection result of the gas detection data is determined based on the secondary detection result, which may include: calculating the target element characteristic value based on the percentage value of the first gas component content and the percentage value of the second gas component content; comparing the target element characteristic value with the target element characteristic threshold interval to obtain the abnormal detection result of the gas detection data.

[0080] Among them, the target element characteristic value can be the target element characteristic value calculated by the target element characteristic model by inputting the percentage value of the first gas component content and the percentage value of the first gas component content into the target element characteristic model, and is used to characterize whether the gas detection data of the first gas component has an abnormality. The target element characteristic value is used to perform a secondary detection on whether the gas detection data has an abnormality when the first detection result of the gas detection data is no abnormality. The target element characteristic threshold range can be a reference numerical range when performing a second detection on whether the gas detection data is abnormal. It can be used as a basis for judging whether the data detection result of the first gas component is abnormal when performing a second detection on whether the gas detection data is abnormal.

[0081] Optionally, the target element characteristic value is calculated based on the percentage value of the first gas component content and the percentage value of the second gas component content. The percentage value of the first gas component content and the percentage value of the second gas component content can be input into a pre-trained target element characteristic model, and the target element characteristic model can calculate the target element characteristic value based on the percentage value of the first gas component content and the percentage value of the second gas component content.

[0082] Optionally, the target element characteristic value is compared with the attribution relationship of the target element characteristic threshold interval to obtain the abnormality detection result of the gas detection data. This can be after calculating the target element characteristic value based on the percentage value of the first gas component content and the percentage value of the second gas component content, comparing the target element characteristic value with the upper limit value and the lower limit value of the target element characteristic threshold interval. If the target element characteristic value is less than the upper limit value of the target element characteristic threshold interval and greater than the lower limit value of the target element characteristic threshold interval, that is, the target element characteristic value is within the target element characteristic threshold interval, then the abnormality detection result of the gas detection data is determined to be no abnormality. If the target element characteristic value is greater than the upper limit value of the target element characteristic threshold interval and / or less than the lower limit value of the target element characteristic threshold interval, that is, the target element characteristic value is not within the target element characteristic threshold interval, then the abnormality detection result of the gas detection data is determined to be no abnormality.

[0083] In an optional embodiment of the present invention, calculating the characteristic value of the target element based on the percentage value of the first gas component content and the percentage value of the second gas component content may include: calculating a target element characteristic model based on the sample data collected from the gas components; wherein the target element characteristic model includes the first gas component content and the second gas component content; inputting the percentage value of the first gas component content and the percentage value of the second gas component content into the target element characteristic model to obtain the characteristic value of the target element.

[0084] The first gas component content may be a percentage value of the first gas component content, and the second gas component content may be a percentage value of the second gas component content.

[0085] The gas composition sample data may be used as sample data for training a target element characteristic model. The gas composition sample data may include a first gas component content and a second gas component content containing the same element as the first gas data.

[0086] The target element characteristic model may be a model for performing secondary detection on gas detection data, and may be obtained by training based on sample data collected based on gas composition.

[0087] Optionally, calculating the target element characteristic model based on the gas composition sample data can include inputting the content of a first gas component in the gas composition sample data and the content of a second gas component containing the same element as the first gas data into the target element characteristic model to be trained, and adjusting the target element characteristic model to be trained based on the value output by the target element characteristic model until the value output by the target element characteristic model to be trained is less than a set error value. If the value output by the target element characteristic model to be trained is less than the set error value, the target element characteristic model to be trained is determined as the target element characteristic model.

[0088] Optionally, the percentage value of the first gas component content and the percentage value of the second gas component content are input into the target element characteristic model to obtain the target element characteristic value. This can be when the abnormal detection result of the first gas detection data is normal, and the percentage value of the first gas component content and the percentage value of the second gas component content are input into the pre-trained target element characteristic model. The target element characteristic value for secondary detection of the gas detection data is calculated by the target element characteristic model.

[0089] Optionally, calculating a target element characteristic model based on sample data collected from gas composition may include:

[0090] Acquire current operating condition information, pre-process the percentage values ​​of the first gas component content and the second gas component content in the flue gas under the current operating condition, and obtain a gas component collection sample data set under the current operating condition;

[0091] Inputting a gas composition sample data set under current working conditions into a pre-built formula, and adjusting the pre-built formula until an error value of the pre-built formula is less than an error threshold;

[0092] The formula obtained by calculation that meets the set conditions is determined as the target element characteristic model.

[0093] Among them, the pre-constructed formula can be constructed or improved by people in this field based on their experience, and can be simple addition, subtraction, multiplication and division or complex operations. Preferably, the pre-constructed formula can be a clearly expressed mathematical formula; the error threshold can be a threshold value set by the user according to the detection requirements or detection accuracy, etc., and the setting condition can be that the error value of the value calculated by the pre-constructed formula is less than the error threshold. Among them, the target element characteristic threshold interval can be an interval range, which can be used for secondary detection of whether the gas detection data is abnormal. Among them, the target element characteristic threshold interval can be obtained by inputting the gas component collection sample data set into the target element characteristic model in turn for calculation to obtain a result data set, and then adding and summing the data in the result data set to obtain the mean data, and then adding the mean data to the error threshold as the upper limit of the target element characteristic threshold interval, and subtracting the error threshold from the mean data as the lower limit of the target element characteristic threshold interval.

[0094] In a specific example, assuming that the target element characteristic threshold interval is a carbon-oxygen characteristic range, the upper limit of the carbon-oxygen characteristic range and the lower limit of the carbon-oxygen characteristic range can be determined by the following steps:

[0095] Step 1: Continuously test the flue gas composition to obtain continuous data of various working conditions;

[0096] Step 2: Manually remove data rows with CO2 detection values ​​less than 1 and outlier data to obtain the basic data set;

[0097] Step 3: Establish the relationship between CO2 and O2 data: y = f(CO2, O2). f can be simple addition, subtraction, multiplication, or division, or complex operations, but must be clearly expressed as a mathematical formula. Where f is the calculation formula, y is the carbon and oxygen characteristic value, CO2 is the percentage value of carbon dioxide content, and O2 is the percentage value of oxygen content.

[0098] Step 4: Calculate y based on the basic data set according to f, and then calculate the average of the absolute deviations of y from its mean, that is, the dispersion;

[0099] Step 5: Continuously adjust f to make the discreteness less than a certain value, that is, the feature deviates from the threshold;

[0100] Step 6: The upper limit of the carbon and oxygen characteristic range = the average value corresponding to y + the characteristic deviation threshold; the lower limit of the carbon and oxygen characteristic range = the average value corresponding to y - the characteristic deviation threshold.

[0101] For example, after experiments, those skilled in the art have obtained the following two formulas that can be used in different scenarios:

[0102] Formula 1: y = f(CO2, O2) = CO2 + O2 + (1 + CO2 / O2) * 6

[0103] The above formula is applicable to the flue gas detection scenario of a certain F-class gas unit. The target element characteristic threshold interval is the carbon and oxygen characteristic range, and the carbon and oxygen characteristic range is 19.88±0.3%. In the formula, f is the calculation formula, y is the carbon and oxygen characteristic value, CO2 is the percentage value of carbon dioxide content, and O2 is the percentage value of oxygen content.

[0104] Formula 2: y = f(CO2, O2) = CO2 + O2 + (1 + CO2 / O2) * 0.2

[0105] Among them, the above formula can be applied to the flue gas detection scenario of a subcritical coal-fired unit. The target element characteristic threshold interval is the carbon and oxygen characteristic range, and the carbon and oxygen characteristic range is 19.97±0.4%. In the formula, f is the calculation formula, y is the carbon and oxygen characteristic value, CO2 is the percentage value of carbon dioxide content, and O2 is the percentage value of oxygen content.

[0106] In an optional embodiment of the present invention, comparing the attribution relationship between the target element characteristic value and the target element characteristic threshold interval to obtain the abnormal detection result of the gas detection data may include: when it is determined that the target element characteristic value is within the target element characteristic threshold interval, determining that the detection result of the gas detection data is normal; when it is determined that the target element characteristic value is outside the target element characteristic threshold interval, determining that the detection result of the gas detection data is abnormal.

[0107] Specifically, when it is determined that the target element characteristic value is within the target element characteristic threshold range, the detection result of the gas detection data is determined to be normal. It can be that after the target element characteristic value is calculated, if the target element characteristic value is within the target element characteristic threshold range, the detection result of the gas detection data is determined to be normal.

[0108] Specifically, when it is determined that the target element characteristic value is outside the target element characteristic threshold range, the detection result of the gas detection data is determined to be abnormal. It can be that after the target element characteristic value is calculated, if the target element characteristic value is not within the target element characteristic threshold range, the detection result of the gas detection data is determined to be abnormal.

[0109] In a specific application scenario, the gas data anomaly detection method provided by an embodiment of the present invention may include the following process:

[0110] Step 1: Detect the flue gas to be tested using a detection instrument.

[0111] Step 2: Obtain the carbon dioxide and oxygen detection signals output by the detection instrument and send them to the controller.

[0112] Step 3: The controller converts the received carbon dioxide and oxygen detection signals into percentage values ​​of carbon dioxide content and oxygen content.

[0113] Step 4: Determine whether the percentage values ​​of the carbon dioxide content and the oxygen content are within corresponding threshold ranges, and perform a first abnormality detection on the gas detection data detected by the detection instrument based on the judgment result.

[0114] Step 5. If the result of the first abnormality detection is that there is no abnormality in the gas detection data detected by the detection instrument, the carbon and oxygen characteristic value is calculated by the formula y = f(CO2, O2), and then it is determined whether the carbon and oxygen characteristic value is within the carbon and oxygen characteristic range. According to the judgment result, a second abnormality detection is performed on the gas detection data detected by the detection instrument.

[0115] The above process determines whether the percentage values ​​of the carbon dioxide content and the percentage values ​​of the oxygen content are within the corresponding threshold ranges, and performs a first abnormality detection on the gas detection data detected by the detection instrument based on the judgment results. If the first abnormality detection result shows that the gas detection data detected by the detection instrument is normal, the carbon and oxygen characteristic values ​​are calculated using the formula y = f(CO2, O2). Then, it is determined whether the carbon and oxygen characteristic values ​​are within the carbon and oxygen characteristic range. Based on the judgment results, a second abnormality detection is performed on the gas detection data detected by the detection instrument. This process can identify abnormal carbon dioxide concentration data within a common value range. The formula can be written to the host computer or PLC, which can accurately detect whether the gas detection data is abnormal while occupying a small space.

[0116] The technical solution of the embodiment of the present invention, when it is determined that the first gas component content detection result and the second gas component content detection result are both normal, can obtain the target element characteristic model by calculating the percentage value of the first gas component content and the percentage value of the second gas component content, and then obtain the target element characteristic value by calculating the target element characteristic model, and finally obtain the abnormal detection result of the gas detection data by judging whether the target element characteristic value is within the target element characteristic threshold range. When the abnormal detection result of the first gas detection data is no abnormality, the target element characteristic value can be calculated by the target element characteristic model, and the gas detection data can be secondary detected by the target element characteristic value to ensure the accuracy of the abnormal detection result of the gas detection data. Moreover, the target element characteristic model is a formula, which occupies less memory and can be written to the host computer or PLC. It can accurately detect whether the gas detection data is abnormal on the basis of occupying a small space.

[0117] Example 3

[0118] Figure 4 This is a schematic diagram of the structure of a gas data anomaly detection device provided by the fourth embodiment of the present invention. Figure 4 As shown, the device includes: a data acquisition module 310, a first gas detection module 320, a second gas detection module 330, and a data anomaly detection module 340.

[0119] The data acquisition module 310 is used to obtain the percentage value of the first gas component content and the percentage value of the second gas component content in the gas detection data output by the gas detection device;

[0120] The first gas detection module 320 is used to detect abnormalities in the percentage value of the first gas component content and obtain a detection result of the first gas component content;

[0121] The second gas detection module 330 is used to detect abnormalities in the percentage value of the second gas component content and obtain a detection result of the second gas component content;

[0122] A data anomaly detection module 340 is configured to determine an abnormality detection result of the gas detection data based on the first gas component content detection result and the second gas component content detection result;

[0123] The first gas component and the second gas component in the gas detection data include the same component elements.

[0124] Furthermore, the first gas detection module 320 is specifically configured to:

[0125] The percentage value of the first gas component content is compared with the attribution relationship of the preset first gas component threshold range to obtain the first gas component content detection result.

[0126] Furthermore, the second gas detection module 330 is specifically configured to:

[0127] The percentage value of the second gas component content is compared with the attribution relationship of the preset second gas component threshold range to obtain the detection result of the second gas component content.

[0128] Furthermore, the gas data anomaly detection device further includes:

[0129] a gas component threshold interval determination module, configured to obtain gas component detection data obtained by continuously performing gas detection by the gas detection device in a set working state before obtaining the percentage value of the first gas component content and the percentage value of the second gas component content in the gas detection data output by the gas detection device;

[0130] The preset first gas component threshold interval and the preset second gas component threshold interval are determined according to the percentage value of the first gas component content and the percentage value of the second gas component content in the gas component detection data.

[0131] Furthermore, the second gas detection module 330 is specifically configured to:

[0132] It is determined whether the percentage value of the second gas component content is within a preset second gas component threshold range, and a second gas component content detection result is obtained according to the determination result.

[0133] Furthermore, the data anomaly detection module 340 is specifically configured to:

[0134] In the case where it is determined that the first gas component content detection result and / or the second gas component content detection result are both abnormal, determining that the detection result of the gas detection data is abnormal;

[0135] When it is determined that the first gas component content detection result and the second gas component content detection result are both normal, the gas detection data is subjected to a secondary detection based on the percentage value of the first gas component content and the percentage value of the second gas component content, and the abnormal detection result of the gas detection data is determined based on the secondary detection result.

[0136] Furthermore, the data anomaly detection module 340 is further configured to:

[0137] Calculating a target element characteristic value according to the percentage value of the first gas component content and the percentage value of the second gas component content;

[0138] The attribution relationship between the target element characteristic value and the target element characteristic threshold interval is compared to obtain the abnormality detection result of the gas detection data.

[0139] Furthermore, the data anomaly detection module 340 is further configured to:

[0140] Calculate a target element characteristic model based on the sample data collected from the gas composition; wherein the target element characteristic model includes a first gas component content variable and a second gas component content variable;

[0141] The percentage value of the first gas component content and the percentage value of the first gas component content are input into the target element characteristic model to obtain the target element characteristic value.

[0142] Furthermore, the data anomaly detection module 340 is further configured to:

[0143] When it is determined that the target element characteristic value is within the target element characteristic threshold range, determining that the detection result of the gas detection data is normal;

[0144] When it is determined that the target element characteristic value is outside the target element characteristic threshold range, the detection result of the gas detection data is determined to be abnormal.

[0145] The above-mentioned gas data anomaly detection device can execute the gas data anomaly detection method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in this embodiment, please refer to the gas data anomaly detection method provided by any embodiment of the present invention.

[0146] Example 4

[0147] Figure 5 A schematic diagram of the structure of an electronic device 10 that can be used to implement 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, workstations, 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 claimed herein.

[0148] like Figure 5As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. 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 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0149] Multiple 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 magnetic 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 via a computer network such as the Internet and / or various telecommunication networks.

[0150] The processor 11 can be any general-purpose and / or specialized processing component 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 specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the gas data anomaly detection method.

[0151] In some embodiments, the gas data anomaly detection method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the gas data anomaly detection method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the gas data anomaly detection method in any other suitable manner (e.g., via firmware).

[0152] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes 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.

[0153] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0154] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0155] To provide interaction with a user, the systems and techniques described herein can 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 pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0156] The systems and techniques described herein can be implemented in a computing system that includes back-end 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 front-end components (e.g., a user computer with a graphical user interface or 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 back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0157] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0158] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0159] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for detecting gas data anomaly, characterized in that: include: Obtaining a percentage value of a first gas component content and a percentage value of a second gas component content in gas detection data output by a gas detection device, wherein the percentage value of the first gas component content is used to represent a percentage value of the first gas component in the exhaust gas, and the percentage value of the second gas component content is used to represent a percentage value of the second gas component in the exhaust gas; Performing an abnormality detection on the percentage value of the first gas component content to obtain a first gas component content detection result, wherein the first gas component content detection result is used to indicate whether the first gas component content is abnormal; Performing an abnormality detection on the percentage value of the second gas component content to obtain a second gas component content detection result, wherein the second gas component content detection result is used to indicate whether the second gas component content is abnormal; determining an abnormality detection result of the gas detection data according to the first gas component content detection result and the second gas component content detection result; wherein the first gas component and the second gas component in the gas detection data include the same component elements; The determining the abnormality detection result of the gas detection data according to the first gas component content detection result and the second gas component content detection result includes: In the case where it is determined that the first gas component content detection result and / or the second gas component content detection result are both abnormal, determining that the detection result of the gas detection data is abnormal; When it is determined that both the first gas component content detection result and the second gas component content detection result are normal, performing a secondary detection on the gas detection data according to the percentage value of the first gas component content and the percentage value of the second gas component content, and determining an abnormal detection result of the gas detection data according to the secondary detection result; Before obtaining the percentage value of the first gas component content and the percentage value of the second gas component content in the gas detection data output by the gas detection device, the method further includes: Acquiring gas composition detection data obtained by the gas detection device through continuous gas detection in a set working state; Determining a preset first gas component threshold interval and a preset second gas component threshold interval according to the percentage value of the first gas component content and the percentage value of the second gas component content in the gas component detection data; The performing secondary detection on the gas detection data according to the percentage value of the first gas component content and the percentage value of the second gas component content, and determining the abnormality detection result of the gas detection data according to the secondary detection result, includes: Calculating a target element characteristic value according to the percentage value of the first gas component content and the percentage value of the second gas component content; Comparing the target element characteristic value with the target element characteristic threshold interval attribution relationship to obtain an abnormality detection result of the gas detection data; The calculating the target element characteristic value according to the percentage value of the first gas component content and the percentage value of the second gas component content includes: Calculate a target element characteristic model based on the sample data collected from the gas composition; wherein the target element characteristic model includes a first gas component content variable and a second gas component content variable; The percentage value of the first gas component content and the percentage value of the first gas component content are input into the target element characteristic model to obtain the target element characteristic value.

2. The method according to claim 1, characterized in that The performing abnormality detection on the percentage value of the first gas component content to obtain the first gas component content detection result includes: Comparing the percentage value of the first gas component content with the attribution relationship of the preset first gas component threshold range to obtain the first gas component content detection result; The performing abnormality detection on the percentage value of the second gas component content to obtain the second gas component content detection result includes: The percentage value of the second gas component content is compared with the attribution relationship of the preset second gas component threshold range to obtain the detection result of the second gas component content.

3. The method according to claim 1, characterized in that The determining whether the target element characteristic value is within the target element characteristic threshold range, and obtaining the abnormality detection result of the gas detection data according to the determination result, includes: When it is determined that the target element characteristic value is within the target element characteristic threshold range, determining that the detection result of the gas detection data is normal; When it is determined that the target element characteristic value is outside the target element characteristic threshold range, the detection result of the gas detection data is determined to be abnormal.

4. A gas data anomaly detection device, characterized in that: include: a data acquisition module, configured to acquire a percentage value of a first gas component content and a percentage value of a second gas component content in gas detection data output by a gas detection device, wherein the percentage value of the first gas component content is used to represent a percentage value of the first gas component in the exhaust gas, and the percentage value of the second gas component content is used to represent a percentage value of the second gas component in the exhaust gas; a first gas detection module, configured to perform abnormality detection on a percentage value of the first gas component content to obtain a first gas component content detection result, wherein the first gas component content detection result is used to indicate whether the first gas component content is abnormal; a second gas detection module, configured to perform abnormality detection on a percentage value of the second gas component content to obtain a second gas component content detection result, wherein the second gas component content detection result is used to indicate whether the second gas component content is abnormal; a data anomaly detection module, configured to determine an anomaly detection result of the gas detection data based on the first gas component content detection result and the second gas component content detection result; wherein the first gas component and the second gas component in the gas detection data include the same component elements; The data anomaly detection module is specifically used to: In the case where it is determined that the first gas component content detection result and / or the second gas component content detection result are both abnormal, determining that the detection result of the gas detection data is abnormal; When it is determined that both the first gas component content detection result and the second gas component content detection result are normal, performing a secondary detection on the gas detection data according to the percentage value of the first gas component content and the percentage value of the second gas component content, and determining an abnormal detection result of the gas detection data according to the secondary detection result; a gas component threshold interval determination module, configured to obtain gas component detection data obtained by continuously performing gas detection by the gas detection device in a set working state before obtaining the percentage value of the first gas component content and the percentage value of the second gas component content in the gas detection data output by the gas detection device; Determining a preset first gas component threshold interval and a preset second gas component threshold interval according to the percentage value of the first gas component content and the percentage value of the second gas component content in the gas component detection data; The data anomaly detection module is also used to: Calculating a target element characteristic value according to the percentage value of the first gas component content and the percentage value of the second gas component content; Comparing the attribution relationship between the target element characteristic value and the target element characteristic threshold interval to obtain an abnormality detection result of the gas detection data; The data anomaly detection module is also used to: Calculate a target element characteristic model based on the sample data collected from the gas composition; wherein the target element characteristic model includes a first gas component content variable and a second gas component content variable; The percentage value of the first gas component content and the percentage value of the first gas component content are input into the target element characteristic model to obtain the target element characteristic value.

5. 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 perform the gas data anomaly detection method according to any one of claims 1 to 3.

6. A readable storage medium, characterized in that: The readable storage medium stores control instructions, and the control instructions are used to enable a processor to implement the gas data anomaly detection method according to any one of claims 1 to 3 when executed.

7. A computer program product comprising a computer program / instructions, wherein: When the computer program / instructions are executed by a processor, the gas data anomaly detection method according to any one of claims 1 to 3 is implemented.

Images