Abnormality reminding method and device based on odor, equipment, medium and program product

Abstract

The invention provides a smell-based abnormity reminding method, device and equipment, a medium and a program product. The method comprises the following steps: acquiring at least one kind of smell sensing data inside to-be-detected equipment; aiming at each kind of smell sensing data, extracting data change characteristics of the kind of smell sensing data to obtain smell characteristic data corresponding to the kind of smell sensing data; the smell characteristic data is used for representing the smell change condition in the to-be-detected equipment; respectively determining the data deviation degree of the smell characteristic data corresponding to each kind of smell sensing data; and according to the data deviation degree, determining whether the operation state of the to-be-tested equipment is abnormal, and when it is determined that the operation state is abnormal, sending reminding information. The reminding information can be sent in time when the running state of the to-be-tested equipment is abnormal, the abnormity reminding precision is improved, and the abnormity reminding cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of odor monitoring, and in particular to an odor-based abnormality reminder method, device, equipment, medium and program product. Background Art

[0002] The power supply and distribution system mainly includes high and low voltage switchgear, cable wells, cable interlayers, high voltage inverters and other equipment, which work together to ensure the smooth operation of the power supply and distribution system. In order to ensure the smooth operation of the power supply and distribution system, it is necessary to monitor the operating status of the above equipment in real time and remind users in time when the operating status is abnormal, so as to avoid affecting the normal operation of the entire power supply and distribution system.

[0003] Among them, the common abnormal operating conditions in high and low voltage switchgear, cable wells, cable interlayers and high voltage inverters mainly include: slight partial discharge and cable overheating. When the equipment has slight partial discharge or cable overheating, although the equipment can still maintain operation, its operating state has become abnormal, which always threatens the safe operation of the power supply and distribution system. Therefore, it is necessary to monitor the operating state of the equipment in the power supply and distribution system in real time so as to promptly remind the user when the operating state is abnormal.

[0004] In the related art, pulse current method, ultra-high frequency method, transient earth voltage (TEV) method, ultrasonic detection method and other methods are usually used to monitor whether partial discharge occurs in high and low voltage switch cabinets, cable wells, cable interlayers and high-voltage inverters. However, the pulse current method is sensitive to sudden changes in signals, but its anti-electromagnetic interference ability is not strong and it is easily affected by electromagnetic interference. Ultrasonic detection method and ultra-high frequency method can effectively avoid the influence of electromagnetic interference, but the propagation characteristics of ultrasonic signals and ultra-high frequency electromagnetic wave signals inside the equipment are not easy to analyze, which makes it difficult to determine the detection results; TEV method detects partial discharge by capturing the instantaneous voltage signal to the ground generated on the surface of the equipment shell when the electromagnetic wave propagates in the air and the surface of the equipment shell, but it cannot quantitatively analyze the partial discharge amount and is easily interfered by external signals. In addition, most of the monitoring equipment used for partial discharge monitoring according to the above method is expensive, ranging from hundreds of thousands to more than one million. In addition, the above monitoring method also requires long-term learning and experience accumulation of monitoring personnel to ensure a certain monitoring accuracy.

[0005] In related technologies, distributed optical fiber temperature measurement technology, infrared imaging technology, HeatTag wireless sensors, etc. are usually used to monitor cable temperature, thereby realizing the monitoring of cable overheating. However, most of the above temperature measurement methods require the use of professional temperature measurement equipment, which has high installation and maintenance costs, and its temperature measurement results are also affected by the installation location and usage, which makes it impossible to effectively guarantee the temperature measurement accuracy. In summary, in the related technologies, most of the monitoring methods for abnormal conditions such as partial discharge and cable overheating have the problem of high monitoring costs and being easily affected by external interference, resulting in the inability to ensure high monitoring accuracy. Summary of the invention

[0006] The embodiments of the present invention provide an odor-based abnormal reminder method, device, electronic device and storage medium to solve the problems of high monitoring cost and low monitoring accuracy when monitoring whether the operating status of each device in the power supply and distribution system is abnormal.

[0007] In a first aspect, an embodiment of the present invention provides an abnormal reminder method based on smell, comprising: Acquiring at least one type of odor sensing data inside the device under test; For each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor characteristic data corresponding to the odor sensing data; the odor characteristic data is used to characterize the odor change in the device to be tested; respectively determining the data deviation of the odor characteristic data corresponding to each type of odor sensing data; According to the data deviation, it is determined whether the operating state of the device under test is abnormal, and when it is determined that the operating state is abnormal, a reminder message is sent.

[0008] In a second aspect, an embodiment of the present invention provides an abnormality reminder device based on smell, comprising: An acquisition module, used to acquire at least one kind of odor sensing data inside the device to be tested; Identify modules for: For each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor characteristic data corresponding to the odor sensing data; the odor characteristic data is used to characterize the odor change in the device to be tested; respectively determining the data deviation of the odor characteristic data corresponding to each type of odor sensing data; The reminder module is used to determine whether the operating state of the device under test is abnormal according to the data deviation, and send a reminder message when it is determined that the operating state is abnormal.

[0009] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the processor implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0010] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0011] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements the method in the first aspect or any possible implementation manner of the first aspect.

[0012] The embodiment of the present invention provides an abnormal reminder method, device, equipment, medium and program product based on odor. The odor characteristic data can be determined by the odor sensor data in the device to be tested. Then, by determining the deviation of the odor characteristic data, it is judged whether the operating state of the device to be tested is abnormal, and after determining that the operating state is abnormal, a reminder message is sent. Among them, the odor characteristic data can be used to characterize the odor change in the device to be tested, and accordingly, the deviation of the odor characteristic data can be used to characterize the degree of odor change in the device to be tested. This is because the inventors consider that when the device to be tested has abnormal operating conditions such as partial discharge or cable overheating, a corresponding special odor is usually generated. Therefore, the embodiment of the present invention monitors the abnormal state by monitoring the degree of odor change to determine whether the operating state of the device to be tested is abnormal, and this method will not be affected by external interference such as electromagnetic environment, installation location, and experience of monitoring personnel. Moreover, since the device to be tested is usually a semi-enclosed environment, it will also facilitate the accurate capture of the odor situation inside the device to be tested, so as to timely discover the abnormal operating state of the device to be tested and improve the accuracy of abnormal monitoring. In addition, the odor-based abnormal reminder method provided by the present application is lower in cost and more economically feasible. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a flow chart of an implementation of an odor-based abnormal reminder method provided by an embodiment of the present invention; Figure 2 is a schematic diagram of a display interface provided by an embodiment of the present invention; Figure 3 is a schematic diagram of multiple preset data intervals and their corresponding data anomaly marking values ​​provided by an embodiment of the present invention; Figure 4 This is a flowchart for determining data abnormality marking values ​​corresponding to various odor characteristic data provided by an embodiment of the present invention; Figure 5 is a flowchart for determining whether the operating state of a device under test is abnormal, provided by an embodiment of the present invention; Figure 6is a flowchart for implementing monitoring of the fault status of a device under test based on odor sensing data provided by another embodiment of the present invention; Figure 7 is a flowchart for determining third sensor data provided by another embodiment of the present invention; Figure 8 is a flowchart for determining odor characteristic data provided by another embodiment of the present invention; Fig. 9 is a schematic structural diagram of an odor-based abnormality reminder device provided in an embodiment of the present invention; Fig.10 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0014] In the related art, different monitoring methods are mostly used to monitor different abnormal conditions. For example, for slight partial discharge, pulse current method, ultra-high frequency method, transient earth voltage (TEV) method, ultrasonic detection method and other methods are usually used. However, the pulse current method is sensitive to sudden change signals, but its anti-electromagnetic interference ability is not strong and it is easily affected by electromagnetic interference. Ultrasonic detection method and ultra-high frequency method can effectively avoid the influence of electromagnetic interference, but the propagation characteristics of ultrasonic signals and ultra-high frequency electromagnetic wave signals inside the equipment are not easy to analyze, which makes it difficult to determine the detection results; TEV method detects partial discharge by capturing the instantaneous voltage signal to the ground generated on the surface of the equipment shell when the electromagnetic wave propagates in the air and the surface of the equipment shell, but it cannot quantitatively analyze the partial discharge amount and is easily interfered by external signals. In addition, the monitoring equipment used for partial discharge monitoring according to the above method is mostly expensive, ranging from hundreds of thousands to more than one million. In addition, the above monitoring method also requires long-term learning and experience accumulation of monitoring personnel to ensure a certain monitoring accuracy.

[0015] For cable overheating, distributed optical fiber temperature measurement technology, infrared imaging technology, HeatTag wireless sensors, etc. are usually used to monitor cable temperature, thereby realizing cable overheating monitoring. However, most of the above temperature measurement methods require the use of professional temperature measurement equipment, which has high installation and maintenance costs, and its temperature measurement results are also affected by the installation location and usage, which makes it impossible to effectively guarantee the temperature measurement accuracy. In summary, in the related technologies, most of the monitoring methods for abnormal conditions such as partial discharge and cable overheating have the problem of high monitoring costs and being easily affected by external interference, resulting in the inability to ensure high monitoring accuracy.

[0016] In order to improve the accuracy of abnormal monitoring of each device in the power supply and distribution system, timely discover the abnormal operating status of the equipment, and at the same time, improve economic feasibility, in the implementation mode of the present application, based on the data deviation of the odor characteristic data in the device to be tested, it is determined whether the operating status of the device to be tested is abnormal, and when it is determined that the operating status is abnormal, a reminder message is sent to remind the user in time. Among them, the odor characteristic data can be used to characterize the odor change in the device to be tested, and accordingly, the data deviation of the odor characteristic data can be used to characterize the degree of odor change in the device to be tested. The inventors have found that when the operating status of the device to be tested is abnormal, for example, when a slight partial discharge or cable overheating occurs, the odor inside the device to be tested will also change accordingly. Therefore, the present application can determine whether the operating status of the device to be tested is abnormal based on the degree of odor change in the device to be tested. On the one hand, the odor monitoring method belongs to the chemical monitoring method and will not be affected by external interference such as the electromagnetic environment, installation location, and experience of the monitoring personnel. On the other hand, the various equipment in the power supply and distribution system (for example, high and low voltage switchgear, cable wells, cable interlayers, and high-voltage inverters, etc.) are usually semi-enclosed environments, which is convenient for accurately capturing the odor inside the equipment, so as to timely discover the abnormal operating status of the equipment to be tested and improve the accuracy of abnormal monitoring. Moreover, the odor-based abnormal reminder method provided by the present application is lower in cost and more economically feasible. In addition, the present application can simultaneously realize monitoring reminders for different abnormal conditions such as partial discharge and cable overheating based on odor changes, without the need to use different monitoring methods for different abnormal operating conditions.

[0017] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0018] Figure 1 The implementation flow chart of the smell-based abnormal reminder method provided by the embodiment of the present invention is detailed as follows: Step 101, obtaining at least one kind of odor sensing data inside the device to be tested.

[0019] Here, the equipment to be tested includes but is not limited to: high and low voltage switch cabinets, cable wells, cable interlayers, and high voltage inverters.

[0020] In the embodiment of the present invention, a semiconductor gas sensor, an olfactory sensor or an odor sensor may be used to collect odor sensing data. The odor sensing data may be used to characterize the odor condition inside the device to be tested.

[0021] Semiconductor gas sensors, olfactory sensors or odor sensors can respond to multiple gas types and volatile substances in a cross-interference manner to generate sensing data to achieve the purpose of identifying gases or odors of single or complex components, thereby reflecting the odor and gas conditions inside the device under test.

[0022] The above-mentioned sensor data can be called odor sensor data or gas sensor data. For the convenience of description, they are collectively referred to as odor sensor data below. It is understandable that when a certain sensor recognizes different types and concentrations of gases and / or volatile substances, the numerical value of the odor sensor data generated by it also changes accordingly. Depending on the type of sensor, the data representation form of the collected odor sensor data is different, and can usually be expressed in the form of voltage value, current value or resistance value.

[0023] In the embodiment of the present invention, a plurality of semiconductor gas sensors, olfactory sensors or odor sensors may be arranged inside the device to be tested to form a sensor array for collecting a variety of odor sensing data. Here, each sensor collects a corresponding type of odor sensing data.

[0024] Here, when selecting the sensor type, it can be determined based on the smell produced when the operating state of the device to be tested is abnormal. Taking high and low voltage switch cabinets as an example, common abnormal states of high and low voltage switch cabinets mainly include slight partial discharge or cable overheating. At this time, even if the high and low voltage switch cabinets can still operate, their operating state has become abnormal. Accordingly, the embodiment of the present invention can select the sensor type based on the smell produced when slight partial discharge or cable overheating occurs.

[0025] For example, taking the high and low voltage switchgear as an example, when partial discharge occurs inside the high and low voltage switchgear, a smell similar to fishy smell will be generated, and when the local discharge intensity is high, a mixed charcoal smell will be generated. This fishy smell or mixed charcoal smell is mainly generated by ozone, carbon monoxide, hydrogen, nitrogen oxides and / or total volatile organic compounds emitted into the air. Accordingly, for partial discharge, a semiconductor gas sensor, olfactory sensor or odor sensor that can respond to ozone, carbon monoxide, hydrogen, nitrogen oxides and / or total volatile organic compounds can be used.

[0026] When the cables in the high and low voltage switch cabinets are overheated, a rubber smell will be generated. When the cables are continuously overheated, the insulation materials will be carbonized, which will produce a burnt smell. This rubber smell is mainly caused by carbon monoxide, methane, carbon dioxide, nitrogen oxides, 2-ethylhexanol, dioctyl terephthalate, benzene, hydrogen chloride, carbon dioxide, alkyl and alkenyl aromatic products, unsaturated hydrogen, ozone, nitrogen oxides and / or aromatic hydrocarbon products emitted into the air. This burnt smell is mainly caused by ammonia, hydrogen, hydrogen sulfide and / or hydrocarbons emitted into the air.

[0027] Accordingly, for cable overheating, a semiconductor gas sensor, olfactory sensor or odor sensor that can respond to carbon monoxide, methane, carbon dioxide, nitrogen oxides, 2-ethylhexanol, dioctyl terephthalate, benzene, hydrogen chloride, carbon dioxide, alkyl and alkenyl aromatic products, unsaturated hydrogen, ozone, nitrogen oxides, aromatic hydrocarbon products, ammonia, hydrogen, hydrogen sulfide and other products and / or hydrocarbons can be used.

[0028] In summary, the semiconductor gas sensor, olfactory sensor or odor sensor in the embodiments of the present invention can respond to at least one of ozone, carbon monoxide, hydrogen, nitrogen oxides, total volatile organic compounds, methane, carbon dioxide, 2-ethylhexanol, dioctyl terephthalate, benzene, hydrogen chloride, alkyl and alkenyl aromatic products, unsaturated hydrogen, aromatic hydrocarbon products, ammonia and hydrogen sulfide to generate odor sensing data.

[0029] Exemplarily, the embodiment of the present invention may use five semiconductor gas sensors to collect odor sensing data, wherein the five sensors respond to ozone, carbon monoxide, hydrogen, nitrogen oxides and total volatile organic compounds, respectively, and generate five types of odor sensing data.

[0030] In addition, an embodiment of the present invention also provides a display interface for displaying the odor characteristic data corresponding to each sensor to the user. The display interface may include a characteristic data change trend graph and a characteristic data spectrum of the device to be tested. Among them, the horizontal axis of the characteristic data change trend graph is time, and the vertical axis is the odor characteristic data, which is used to characterize the change trend of different types of odor characteristic data inside the device to be tested over time. The characteristic data spectrum mainly includes a line graph and a radar graph. Among them, the horizontal axis of the line graph is different types of sensors, and the vertical axis is the odor characteristic data, which is used to characterize the odor characteristic data corresponding to each sensor in the device to be tested at the current moment. The radar graph is used to characterize the odor characteristic data corresponding to each sensor in the device to be tested at the current moment.

[0031] For example, see Figure 2 , taking the above five sensors as an example, the AH characteristic data change trend chart is the characteristic data change trend chart of the high and low voltage switchgear. The horizontal axis of the AH characteristic data change trend chart is time, and the vertical axis is the odor characteristic data. Through the AH characteristic data change trend chart, users can conveniently observe the change trend of the odor characteristic data corresponding to each sensor at different times. GS1, GS2, GS3, GS4 and GS5 are used to represent sensors that can respond to ozone, carbon monoxide, hydrogen, nitrogen oxides and total volatile organic compounds, respectively. The horizontal axis of the line graph in the sensor data spectrum is different sensors, and the vertical axis is the odor characteristic data. The radar chart is used to characterize the odor characteristic data corresponding to GS1, GS2, GS3, GS4 and GS5.

[0032] Step 102, for each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor characteristic data corresponding to the odor sensing data; the odor characteristic data is used to characterize the odor change in the device under test.

[0033] The odor condition inside the device to be tested can affect the size of the odor sensing data. However, the size of the odor sensing data is not only affected by the odor condition, but also by other external interference factors, such as temperature, humidity, etc. The odor sensing data corresponding to the same odor environment at different temperatures or different humidities are different. Therefore, the embodiment of the present invention does not directly judge whether the operating status of the device to be tested is abnormal based on the size of the odor sensing data, but adopts a method of extracting data change characteristics of the odor sensing data to determine the odor change situation inside the device to be tested, and based on the odor change situation, judge whether the operating status of the device to be tested is abnormal, so as to avoid the adverse effects of external interference factors.

[0034] In some embodiments, for each type of odor sensing data, the specific process of extracting the data change characteristics of the odor sensing data and obtaining the odor characteristic data corresponding to the odor sensing data is as follows: It can be understood that the operation status monitoring process of the equipment to be tested is a real-time online monitoring process. Accordingly, the odor characteristic data corresponding to each type of odor sensing data here may include: the odor characteristic data corresponding to each type of odor sensing data at different times.

[0035] For each type of odor sensing data, first, the second time series data corresponding to the odor sensing data at the current moment is obtained; the second time series data includes the odor sensing data corresponding to the current moment and different moments before the current moment.

[0036] Secondly, the first sensor data is determined according to the average value of the odor sensor data in the third preset time interval in the second time series data corresponding to the current moment. And the second sensor data is determined according to the average value of the odor sensor data in the fourth preset time interval in the second time series data corresponding to the current moment. Here, the third preset time interval is earlier than the fourth preset time interval; the current moment is in the fourth preset time interval.

[0037] Finally, according to the ratio of the first sensing data to the second sensing data, the odor characteristic data corresponding to the odor sensing data at the current moment is determined.

[0038] In essence, the second sensing data can be used to characterize the odor condition of the device under test at the current moment. The first sensing data can be used to characterize the odor condition of the device under test before the current moment.

[0039] Here, the third preset time interval and the fourth preset time interval can be determined by setting parameters such as the third preset time interval length RbSQ, the fourth preset time interval length RgSQ, and the second time interval interval RbSI. Here, the second time interval interval RbSI is used to represent the time difference between the end moment of the third preset time interval and the beginning moment of the fourth preset time interval.

[0040] It can be understood that the third preset time interval length RbSQ and the fourth preset time interval length RgSQ are both integers greater than 1, and the second time interval interval RbSI is an integer greater than or equal to 0. The specific values ​​of the three can be determined according to actual conditions, and the embodiment of the present invention does not specifically limit this.

[0041] Exemplarily, the difference between two adjacent moments is 1 second, that is, the time difference between each data point in the second time series data is 1 second. Taking the current moment as the 15th second as an example, the time series data corresponding to the current moment can be expressed as: R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, R12, R13, R14, R15. Among them, the odor sensor data corresponding to the current moment is R15. The third preset time interval length RbSQ and the fourth preset time interval length RgSQ can both be 6 seconds. The second time interval interval RbSI can be 1 second. Then the fourth preset time interval is the time interval formed from the 10th second to the 15th second, and the corresponding odor sensor data in the fourth preset time interval are R10, R11, R12, R13, R14, R15. The second sensor data is the average value of R10, R11, R12, R13, R14, R15. The third preset time interval is the time interval formed from the 3rd second to the 8th second, and the corresponding odor sensor data in the third preset time interval are R3, R4, R5, R6, R7, and R8. The first sensor data is the average value of R3, R4, R5, R6, R7, and R8.

[0042] In the embodiment of the present invention, the ratio of the first sensing data to the second sensing data can be used to determine the odor characteristic data corresponding to the odor sensing data at the current moment.

[0043] Step 103, respectively determining the data deviation of the odor characteristic data corresponding to each type of odor sensing data.

[0044] The data deviation of the odor characteristic data can be simply understood as the deviation of the odor characteristic data. According to the above, the odor characteristic data can be used to characterize the odor change in the device under test. Accordingly, the data deviation of the odor characteristic data can be used to characterize the degree of odor change in the device under test.

[0045] Here, the odor characteristic data corresponding to each type of odor sensing data may include: the odor characteristic data corresponding to each type of odor sensing data at different times, respectively used to characterize the odor change in the device under test at different times. Correspondingly, the data deviation of each type of odor characteristic data includes: the deviation of each type of odor characteristic data at different times, respectively used to characterize the degree of odor change in the device under test at different times.

[0046] Step 104: determine whether the operating state of the device under test is abnormal based on the data deviation, and send a reminder message when it is determined that the operating state is abnormal.

[0047] The present application takes into account that when the operating state of the device under test is abnormal, a special smell will usually be generated accordingly, thereby causing the smell in the device under test to change accordingly. Therefore, the embodiment of the present invention can determine whether the operating state of the device under test at the corresponding moment is abnormal according to the degree of change of the smell in the device under test at different moments, and send a reminder message when it is determined that the operating state is abnormal, so as to promptly remind the user to inspect and maintain the device under test.

[0048] Compared with the prior art, the embodiment of the present invention can first determine the odor characteristic data according to the odor sensor data in the device to be tested, and then determine whether the operating state of the device to be tested is abnormal by determining the deviation of the odor characteristic data, and send a reminder message after determining that the operating state is abnormal. Among them, the odor characteristic data can be used to characterize the odor change in the device to be tested, and accordingly, the deviation of the odor characteristic data can be used to characterize the degree of odor change in the device to be tested. The method of monitoring the abnormal state by monitoring the degree of odor change in the embodiment of the present invention will not be affected by external interference such as the electromagnetic environment, installation location, and experience of monitoring personnel. In addition, since each device to be tested in the power supply and distribution system (for example, high and low voltage switch cabinets, cable wells, cable interlayers, and high-voltage inverters, etc.) is usually a semi-enclosed environment, it will also facilitate the accurate capture of the odor situation inside the device to be tested, thereby timely discovering the abnormal operating state of the device to be tested and improving the accuracy of abnormal monitoring. In addition, the odor-based abnormal reminder method provided by the present application is lower in cost and more economically feasible.

[0049] According to the above embodiments, the embodiments of the present invention mainly remind the abnormal operation status according to the data deviation of the odor characteristic data. The following focuses on the method for determining the data deviation and the process of determining whether the operation status of the device under test is abnormal according to the data deviation.

[0050] In some embodiments, when determining the data deviation of the odor characteristic data at different times, the following steps AC may be performed: Step A: for each type of odor characteristic data, obtain the first time series data corresponding to the odor characteristic data at the current moment, wherein the first time series data includes the odor characteristic data corresponding to the current moment and different moments before the current moment.

[0051] In the embodiment of the present invention, each sensor disposed in the device to be tested collects odor sensing data in real time, each sensor corresponds to a type of odor sensing data, and each type of odor sensing data corresponds to a type of odor characteristic data. For each type of sensor, the odor characteristic data corresponding to the sensor at the current moment and at different moments before the current moment can be combined in chronological order to form first time series data.

[0052] Step B, determining the first characteristic data and the second characteristic data corresponding to the current moment.

[0053] The first characteristic data is determined by the odor characteristic data in the first preset time interval in the first time series data, and is used to characterize the change of the odor in the device under test in the first preset time interval. The second characteristic data is determined by the odor characteristic data in the second preset time interval in the first time series data, and is used to characterize the change of the odor in the device under test in the second preset time interval.

[0054] In the embodiment of the present invention, the average value of the odor sensor data in the first preset time interval in the time series data can be used as the first characteristic data to characterize the odor situation in the device under test to avoid noise interference. Similarly, the average value of the odor sensor data in the second preset time interval in the time series data can be used as the second characteristic data.

[0055] The first preset time interval is later than the second preset time interval. The current moment is within the first preset time interval. In essence, the first characteristic data can be used to characterize the odor change of the device under test at the current moment. The second characteristic data can be used to characterize the odor change of the device under test before the current moment.

[0056] In the embodiment of the present invention, the first preset time interval and the second preset time interval can be determined by setting parameters such as the first preset time interval length SQ1, the second preset time interval length SQ2, and the first time interval interval SI1. Here, the first time interval interval is used to represent the time difference between the end moment of the first preset time interval and the beginning moment of the second preset time interval.

[0057] It is understandable that the first preset time interval length SQ1 and the second preset time interval length SQ2 are both integers greater than 1, and the first time interval interval SI1 is an integer greater than or equal to 0. The specific values ​​of the three can be determined according to actual conditions, and the embodiment of the present invention does not specifically limit this.

[0058] Exemplarily, the difference between two adjacent moments is 1 second, that is, the time difference between each data point in the first time series data is 1 second. Taking the current moment as the 15th second as an example, the first time series data corresponding to the current moment can be expressed as: RbC1, RbC2, RbC3, RbC4, RbC5, RbC6, RbC7, RbC8, RbC9, RbC10, RbC11, RbC12, RbC13, RbC14, RbC15. Among them, the odor characteristic data corresponding to the current moment is RbC15. The first preset time interval length SQ1 and the second preset time interval length SQ2 can both be 3 seconds. The first time interval interval RaSI can be 3 seconds. Then the first preset time interval is the time interval formed from the 13th second to the 15th second, and the corresponding odor characteristic data in the first preset time interval are RbC13, RbC14, and RbC15. The second preset time interval is the time interval formed from the 7th second to the 9th second, and the corresponding odor characteristic data within the second preset time interval are RbC7, RbC8, and RbC9.

[0059] For intuitive understanding, the embodiment of the present invention provides Table 1 for illustrating the distribution of the first preset time interval and the second preset time interval when the first preset time interval length SQ1, the second preset time interval length SQ2 and the first time interval interval SI1 are at different values. Here, it is assumed that time 10 is the current time.

[0060] Table 1

[0061] Step C, determining the data deviation of the odor characteristic data at the current moment according to the ratio of the first characteristic data to the second characteristic data.

[0062] In the embodiment of the present invention, the change rate of the first characteristic data compared with the second characteristic data can be determined according to the ratio of the first characteristic data to the second characteristic data, and on this basis, the deviation between the change rate and the reference change rate 1 is determined, thereby determining the data deviation of the odor characteristic data at the current moment. The specific formula can be expressed as: .

[0063] in, Indicates the data deviation of the odor characteristic data, represents the first feature data, represents the second characteristic data, represents the absolute value function.

[0064] The data deviation here actually refers to the deviation between the odor change at the current moment and the odor change before the current moment, that is, the real-time odor change degree at the current moment.

[0065] Here, when determining whether the operating state of the device under test is abnormal based on the data deviation, the embodiment of the present invention provides the following two determination methods: The first determination method: determine the sum of the data deviations of various odor characteristic data. If the sum of the data deviations is less than the first preset deviation, it is determined that there is no abnormality in the operating status of the device under test; if the sum of the data deviations is greater than the first preset deviation, it is determined that there is an abnormality in the operating status of the device under test.

[0066] It can be understood that during the operation of the device under test, the embodiment of the present invention can monitor the odor sensor data inside the device under test in real time online, and then determine the odor characteristic data at different times in real time, and based on the odor characteristic data at different times, determine whether there is any abnormality in the operating status of the device under test at the corresponding time.

[0067] The embodiment of the present invention can determine whether the operating status of the device to be tested at the current moment is abnormal based on the relationship between the sum of the data deviations of various odor characteristic data at the current moment and the first preset deviation.

[0068] Here, the value of the first preset deviation can be determined according to actual conditions. For example, the first preset deviation can be 0.2, 0.4 or 0.5, etc.

[0069] The second determination method: first determine the data anomaly mark value corresponding to various odor characteristic data based on the data deviation of various odor characteristic data, then accumulate the data anomaly mark values ​​corresponding to various odor characteristic data, and determine whether the operating status of the equipment under test is abnormal based on the accumulated data anomaly mark values.

[0070] Here, for each moment, the data anomaly mark values ​​corresponding to various odor characteristic data can be determined according to the data deviation of various odor characteristic data at that moment, and then the data anomaly mark values ​​corresponding to various odor characteristic data can be accumulated, and based on the accumulated data anomaly mark values, it can be determined whether the operating status of the equipment under test at that moment is abnormal.

[0071] In some embodiments, for each type of odor characteristic data, a data anomaly flag value of the odor characteristic data is determined according to a preset data interval in which the data deviation of the odor characteristic data is located. Here, there are multiple preset data intervals, and different preset data intervals correspond to different data anomaly flag values.

[0072] Furthermore, the data anomaly mark values ​​corresponding to various odor characteristic data at the current moment are accumulated, and based on the accumulated data anomaly mark values, it is determined whether the operating state of the device under test is abnormal. When the accumulated data anomaly mark value is less than the first preset threshold, it is determined that the operating state of the device under test is normal; when the accumulated data anomaly mark value is greater than or equal to the first preset threshold and less than the second preset threshold, it is determined that the operating state of the device under test is in a first-level abnormal state; when the accumulated data anomaly mark value is greater than or equal to the second preset threshold, it is determined that the operating state of the device under test is in a second-level abnormal state.

[0073] Here, when determining that different preset data intervals correspond to different data anomaly flag values, first preset thresholds, and second preset thresholds, the embodiment of the present invention provides two implementation methods: In one embodiment, there is at least one pair of two adjacent target data intervals in the plurality of preset data intervals, and the difference between the first difference corresponding to the two adjacent target data intervals and the second difference corresponding to the remaining two adjacent data intervals is greater than the preset difference.

[0074] The first difference is the difference between the data anomaly mark values ​​corresponding to two adjacent target data intervals, and the second difference is the difference between the data anomaly mark values ​​corresponding to the remaining two adjacent data intervals.

[0075] Here, multiple preset data intervals can be obtained by splitting a complete data interval. The upper and lower limits of the complete data interval can be determined according to the data deviation of various odor characteristic data. Among them, the upper limit value of the complete data interval is greater than or equal to the maximum value of the data deviation of various odor characteristic data. The lower limit value of the complete data interval is less than or equal to the minimum value of the data deviation of various odor characteristic data.

[0076] In the embodiment of the present invention, the upper limit value of each preset data interval, the data abnormality mark value corresponding to each preset data interval, and the preset difference value can all be determined according to actual conditions. The embodiment of the present invention is not specifically limited by comparison.

[0077] For example, see Figure 3 , the number of preset data intervals can be 5. These 5 preset data intervals can be expressed as [0,0.1), [0.1,0.2), [0.2,0.3), [0.3,0.4) and [0.4,∞). Among them, the data anomaly mark value corresponding to [0,0.1) is 0, the data anomaly mark value corresponding to [0.1,0.2) is 1, the data anomaly mark value corresponding to [0.2,0.3) is 2, the data anomaly mark value corresponding to [0.3,0.4] is 33, and the data anomaly mark value corresponding to [0.4,∞) is 34.

[0078] Here, the difference between the data anomaly marker values ​​corresponding to [0.2, 0.3) and [0.3, 0.4) is greater than the difference between the data anomaly marker values ​​corresponding to [0, 0.1) and [0.1, 0.2), the difference between the data anomaly marker values ​​corresponding to [0.1, 0.2) and [0.2, 0.3), and the difference between the data anomaly marker values ​​corresponding to [0.3, 0.4) and [0.4, ∞). That is, [0.2, 0.3) and [0.3, 0.4) are a pair of adjacent target data intervals.

[0079] The embodiment of the present invention sets a pair of adjacent target data intervals [0.2, 0.3) and [0.3, 0.4) to significantly increase the data anomaly mark value corresponding to the odor characteristic data when the data deviation of the odor characteristic data exceeds 0.3, so that when the abnormal state is subsequently judged according to the accumulated data anomaly mark value, the case where the data deviation is greater than or equal to 0.3 and the case where the data deviation is less than 0.3 can be significantly distinguished, so as to facilitate the subsequent abnormal level classification of the abnormal operating state to distinguish operating states with different abnormal degrees.

[0080] It can be understood that the number of the adjacent target data intervals may be more than one pair, which can be determined according to actual conditions, and the embodiment of the present invention does not specifically limit this.

[0081] Exemplarily, the number of preset data intervals may be 6. These 6 preset data intervals may be expressed as [0, 0.2), [0.2, 0.4), [0.4, 0.6), [0.6, 0.8), [0.8, 1), and [1, ∞). Among them, the data anomaly mark value corresponding to [0, 0.2) is 0, the data anomaly mark value corresponding to [0.2, 0.4) is 1, the data anomaly mark value corresponding to [0.4, 0.6) is 33, the data anomaly mark value corresponding to [0.6, 0.8] is 34, the data anomaly mark value corresponding to [0.8, 1) is 64, and the data anomaly mark value corresponding to [1, ∞) is 65. At this time, [0.2, 0.4) and [0.4, 0.6) can be used as a pair of adjacent target data intervals, and [0.6, 0.8) and [0.8, 1) can be used as another pair of adjacent target data intervals.

[0082] Here, the difference between the first preset threshold and the second preset threshold can be determined according to the difference between the data anomaly mark values ​​corresponding to the two adjacent target data intervals.

[0083] Here, the first preset threshold and the second preset threshold are mainly used to distinguish abnormal states of different levels. According to the above, when setting the data marker abnormal value, the embodiment of the present invention can set a pair of adjacent target data intervals to significantly distinguish the case where the data deviation is greater than or equal to a fixed value, and the case where the data deviation is less than the fixed value. Accordingly, the embodiment of the present invention can determine the difference between the first preset threshold and the second preset threshold according to the difference between the data abnormality marker values ​​corresponding to the pair of adjacent target data intervals, thereby significantly distinguishing the case where the data deviation is greater than or equal to the fixed value, and the case where the data deviation is less than the fixed value, so as to classify them into different abnormal level states respectively.

[0084] Still taking the above five preset data intervals as an example, the five preset data intervals can be expressed as [0, 0.1), [0.1, 0.2), [0.2, 0.3), [0.3, 0.4) and [0.4, ∞). Among them, the data anomaly mark value corresponding to [0, 0.1) is 0, the data anomaly mark value corresponding to [0.1, 0.2) is 1, the data anomaly mark value corresponding to [0.2, 0.3) is 2, the data anomaly mark value corresponding to [0.3, 0.4] is 33, and the data anomaly mark value corresponding to [0.4, ∞) is 34.

[0085] The difference between the data anomaly mark values ​​corresponding to the target data intervals [0.2, 0.3) and [0.3, 0.4) is 31. Accordingly, the difference between the first preset threshold and the second preset threshold can be set to 31. Exemplarily, the first preset threshold can be 2, and the second preset threshold can be 33.

[0086] In another embodiment, based on determining the data deviation of the odor characteristic data corresponding to each sensor, the data anomaly mark value, the first preset threshold value and the second preset threshold value corresponding to each preset data interval are comprehensively determined in combination with the number of sensors.

[0087] Still taking the above-mentioned 5 preset data intervals as an example, the 5 preset data intervals can be expressed as [0, 0.1), [0.1, 0.2), [0.2, 0.3), [0.3, 0.4) and [0.4, ∞). Taking 5 types of sensors as an example, 5 types of odor characteristic data are generated accordingly. In an embodiment of the present invention, the case where the data deviation of two odor characteristic data is in [0.1, 0.2) and the remaining data deviation is 0, or the case where the data deviation of one odor characteristic data is in [0.2, 0.3) and the remaining data deviation is 0, can be used as the lower limit of the first-level abnormal state, which is used to distinguish between the non-abnormal state and the first-level abnormal state. At this time, the data abnormality mark value corresponding to [0, 0.1) can be determined as 0, the data abnormality mark value corresponding to [0.1, 0.2) can be determined as 1, and the data abnormality mark value corresponding to [0.2, 0.3) can be determined as 2. At this time, in the above two cases, the corresponding cumulative data abnormality mark values ​​are both 2. Correspondingly, the first preset threshold is 2.

[0088] In an embodiment of the present invention, the case where the data deviation of all odor characteristic data is in [0.2, 0.3), or the case where the data deviation of one odor characteristic data is in [0.3, 0.4), and the data deviation of the remaining odor characteristic data is in [0.2, 0.3), is used as the upper limit of the first-level abnormal state to distinguish the first-level abnormal state from the second-level abnormal state. At this time, the data anomaly mark value corresponding to [0.3, 0.4) can be determined as 9. The cumulative data anomaly mark values ​​corresponding to the above two situations are both 17.

[0089] On this basis, the embodiment of the present invention uses the case where the data deviation of two types of odor characteristic data are both in [0.3, 0.4) and the remaining data deviations are all 0, or the case where the data deviation of one type of odor characteristic data is in [0.4, ∞) and the remaining data deviations are all 0 as the lower limit of the secondary abnormal state, which is used to distinguish the primary abnormal state from the secondary abnormal state. At this time, the data abnormality mark value corresponding to [0.4, ∞) can be determined as 18. The cumulative data abnormality mark values ​​corresponding to the above two situations are both 18. Accordingly, the second preset threshold value can be equal to 18.

[0090] In summary, taking 5 types of sensors and 5 preset data intervals as an example, the 5 preset data intervals can be expressed as [0, 0.1), [0.1, 0.2), [0.2, 0.3), [0.3, 0.4) and [0.4, ∞). Among them, the data anomaly mark value corresponding to [0, 0.1) is 0, the data anomaly mark value corresponding to [0.1, 0.2) is 1, the data anomaly mark value corresponding to [0.2, 0.3) is determined to be 2, the data anomaly mark value corresponding to [0.3, 0.4) is 9, and the data anomaly mark value corresponding to [0.4, ∞) is determined to be 18. The first preset threshold is 2, and the second preset threshold is 18.

[0091] If the number of sensors is n, still taking the above five preset data intervals as an example, the five preset data intervals can be expressed as [0, 0.1), [0.1, 0.2), [0.2, 0.3), [0.3, 0.4) and [0.4, ∞). Among them, the data anomaly mark value corresponding to [0, 0.1) can be 0, the data anomaly mark value corresponding to [0.1, 0.2) can be 1, the data anomaly mark value corresponding to [0.2, 0.3) can be 2, and the data anomaly mark value corresponding to [0.3, 0.4) can be: 2n-1. The data anomaly mark value corresponding to [0.4, ∞) can be: 4n-2.

[0092] Combine the following Figure 4 and Figure 5 , an overall introduction is given to the process of determining whether the operating status within the equipment to be tested is abnormal based on the odor sensing data.

[0093] See also Figure 4 For each type of odor characteristic data, the first characteristic data (CV) corresponding to the current moment can be determined by using the average value of the odor characteristic data in the first preset time interval (SQ1) in the first time series data RbC corresponding to the current moment. The specific formula can be expressed as: CV=Avg(RbC[0-SQ1],SQ1).

[0094] According to the average value of the odor characteristic data in the second preset time interval (SQ2) in the first time series data RbC corresponding to the current moment, the second characteristic data (BV) corresponding to the current moment is determined. The specific formula can be expressed as: BV=Avg(RbC[0-SQ1-SQ2-SI1],SQ2).

[0095] Next, the data deviation (d) of the odor characteristic data at the current moment is determined based on the absolute value of the difference between the ratio of the first characteristic data (CV) and the second characteristic data (BV) corresponding to the current moment and the reference change rate 1. The specific formula can be expressed as: d=ABS(CV÷BV-1).

[0096] Then, the relationship between the data deviation of the odor characteristic data at the current moment and each preset data interval is determined. Here, the preset data interval can be expressed as: [0, LT11), [LT11, LT12), [LT12, LT21), [LT21, LT22) and [LT22, ∞).

[0097] Finally, according to the preset data interval in which the data deviation of the odor characteristic data at the current moment is located, the data abnormality mark value corresponding to the odor characteristic data at the current moment is determined.

[0098] For example, LT11=0.1, LT12=0.2, LT21=0.3, LT22=0.4. The data anomaly marker value corresponding to [0,LT11) is 0. The data anomaly marker value corresponding to [LT11,LT12) is 1. The data anomaly marker value corresponding to [LT12,LT21) is 2. The data anomaly marker value corresponding to [LT21,LT22) is 9. The data anomaly marker value corresponding to [LT22,∞) is 18.

[0099] See also Figure 5 , on the basis of determining the data anomaly mark value corresponding to various odor characteristic data, accumulate the data anomaly mark value corresponding to each odor characteristic data to obtain the accumulated data anomaly mark value (AMCount). Determine the size relationship between the accumulated data anomaly mark value (AMCount) and the first preset threshold and the second preset threshold, wherein when the accumulated data anomaly mark value (AMCount) is less than the first preset threshold, it is determined that there is no abnormality in the operating state of the device under test. When the accumulated data anomaly mark value (AMCount) is greater than or equal to the first preset threshold and less than the second preset threshold, it is determined that the device under test is in a first-level abnormal state. When the accumulated data anomaly mark value (AMCount) is greater than or equal to the second preset threshold, it is determined that the device under test is in a second-level abnormal state.

[0100] Here, assuming that there are I types of odor characteristic data, the data anomaly mark values ​​corresponding to various odor characteristic data can be expressed as AM[1], ..., AM[I]. For example, when I=5, the first preset threshold value can be 2, and the second preset threshold value can be 18.

[0101] The above embodiment mainly determines whether the operating state of the device under test is abnormal based on the odor sensor data. However, it is not possible to accurately determine the fault state of the device under test based on the odor sensor data. In order to accurately determine the fault state of the device under test, the present invention provides another embodiment for determining the fault state of the device under test based on the odor sensor data. Figure 6 , when determining the fault status of the device under test, you can follow the steps below: Step 601, obtaining at least one kind of odor sensing data inside the device to be tested.

[0102] The specific implementation of step 601 can be found in Figure 1 The corresponding embodiments will not be described in detail here.

[0103] Step 602, for each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor characteristic data corresponding to the odor sensing data; the odor characteristic data is used to characterize the odor change in the device under test.

[0104] Similarly, it is considered that the odor conditions inside the device to be tested can affect the size of the odor sensor data. However, the size of the odor sensor data is not only affected by the odor conditions, but also by other external interference factors, such as temperature, humidity, etc. The odor sensor data corresponding to the same odor environment at different temperatures or different humidities are different. Therefore, the embodiment of the present invention does not directly monitor the fault state of the device to be tested based on the size of the odor sensor data, but adopts a method of extracting data change characteristics of the odor sensor data to determine the odor change situation inside the device to be tested, and based on the odor change situation, monitor the fault state of the device to be tested to avoid the adverse effects of external interference factors.

[0105] Step 603, input the odor characteristic data corresponding to each type of odor sensing data into each pre-trained fault monitoring model to obtain the fault monitoring result output by each fault monitoring model; each fault monitoring model corresponds to a preset fault state; the fault monitoring model determines whether the device is in the corresponding preset fault state based on the odor characteristic data inside the device.

[0106] The odor characteristic data corresponding to each type of odor sensing data can characterize the change of an odor. The embodiment of the present invention monitors the fault state inside the device under test according to the change of each type of odor. In some embodiments, the odor characteristic data corresponding to each type of odor sensing data can be input into each pre-trained fault monitoring model to obtain the fault monitoring results output by each fault monitoring model. Each fault monitoring model corresponds to a preset fault state. The fault monitoring model determines whether the device is in the corresponding preset fault state according to the odor characteristic data inside the device.

[0107] For example, taking high and low voltage switchgear as an example, common fault types of high and low voltage switchgear are partial discharge fault and cable overheating fault. For partial discharge fault, a fault monitoring model for partial discharge fault can be trained based on the odor characteristic data under partial discharge fault. The fault monitoring model is used to determine whether a partial discharge fault occurs in the high and low voltage switchgear according to the input odor characteristic data. Similarly, a fault monitoring model for cable overheating fault can be trained based on the odor characteristic data under cable overheating fault. The fault monitoring model is used to determine whether a cable overheating fault occurs in the high and low voltage switchgear according to the input odor characteristic data.

[0108] It can be understood that fault monitoring of the equipment under test is a real-time online monitoring process. Accordingly, the odor characteristic data corresponding to each type of odor sensing data here may include: odor characteristic data corresponding to each type of odor sensing data at different times.

[0109] For each moment, the odor feature data corresponding to each odor sensor at that moment can be input into each fault monitoring model to determine whether the device under test at that moment is in a fault state. Alternatively, the odor feature data corresponding to each odor sensor at that moment and at different moments before that moment can be input into each fault monitoring model to determine whether the device under test at that moment is in a fault state.

[0110] Compared with the prior art, the embodiment of the present invention can determine the odor characteristic data by extracting the data change characteristics of the odor sensor data inside the device to be tested, and then monitor the fault state of the device to be tested based on the odor characteristic data. Here, the odor characteristic data can be used to characterize the odor changes inside the device to be tested. The embodiment of the present invention performs fault monitoring through the odor changes inside the device to be tested, which will not be affected by external interference such as the electromagnetic environment interference, installation location, and experience of the monitoring personnel inside the device to be tested, and can effectively improve the fault monitoring accuracy. Moreover, the odor-based fault monitoring method provided by the present application has lower cost and is more economically feasible. In addition, the fault monitoring method provided by the embodiment of the present invention can simultaneously realize the monitoring of partial discharge faults and / or cable overheating faults, without the need to monitor the two fault types separately, which can effectively simplify the fault monitoring method.

[0111] According to the above embodiments, the present application mainly determines the odor characteristic data by extracting the data change characteristics of the odor sensor data, thereby realizing the fault monitoring of the device under test. The specific method for determining the odor characteristic data is introduced in detail below.

[0112] It can be understood that the odor characteristic data corresponding to each type of odor sensing data includes: the odor characteristic data corresponding to each type of odor sensing data at different times.

[0113] For each type of odor sensing data, the specific process of extracting the data change characteristics of the odor sensing data and obtaining the odor characteristic data corresponding to the odor sensing data is as follows: For each type of odor sensing data, obtain the second time series data corresponding to the type of odor sensing data at the current moment; the second time series data includes the type of odor sensing data corresponding to the current moment and different moments before the current moment; Determine the third sensor data and the fourth sensor data corresponding to the current moment; the third sensor data is determined by the odor sensor data within the fifth preset time interval in the second time series data, and the fourth sensor data is determined by the odor sensor data within the sixth preset time interval in the second time series data; the fifth preset time interval is earlier than the sixth preset time interval; the current moment is within the sixth preset time interval; According to the ratio of the third sensing data to the fourth sensing data, the odor characteristic data corresponding to the odor sensing data at the current moment is determined.

[0114] The fifth preset time interval is earlier than the sixth preset time interval, and the current moment is within the sixth preset time interval. In essence, the fourth sensing data can be used to characterize the odor condition of the device under test at the current moment. The third sensing data can be used to characterize the odor condition of the device under test before the current moment.

[0115] Similar to the above determination of the first preset time interval, the second preset time interval, the third preset time interval, and the fourth preset time interval, the embodiment of the present invention can determine the fifth preset time interval and the sixth preset time interval by setting parameters such as the fifth preset time interval length RaSQ, the sixth preset time interval length RgSQ', and the third time interval interval RaSI. Here, the third time interval interval is used to indicate the time difference between the end moment of the fifth preset time interval and the beginning moment of the sixth preset time interval. For specific determination methods, please refer to Figure 1 The corresponding embodiments will not be described in detail here.

[0116] It can be understood that the fifth preset time interval length RaSQ and the sixth preset time interval length RgSQ are both integers greater than 1, and the third time interval RaSI is an integer greater than or equal to 0. The specific values ​​of the three can be determined according to actual conditions, and the embodiment of the present invention does not make specific limitations on this.

[0117] For example, the fifth preset time interval length RaSQ and the sixth preset time interval length RgSQ may both be 6 seconds. The third time interval length RaSI may be 1 second.

[0118] In some embodiments, the fourth sensing data corresponding to the current moment can be determined based on the average value of the odor sensing data within the sixth preset time interval in the second time series data corresponding to the current moment.

[0119] Here, the average value of the odor sensor data in the sixth preset time interval in the second time series data corresponding to the current moment can be directly determined as the fourth sensor data corresponding to the current moment. It should be noted that the sixth preset time interval here includes the current moment, that is, the sixth preset time interval can be determined by taking the current moment as the end moment of the sixth preset time interval.

[0120] In some embodiments, when determining the third sensor data corresponding to the current moment, reference data may be obtained first. Here, the reference data is used to characterize the odor sensor data when the odor in the device under test begins to change; then, based on the ratio of the reference data to the fourth sensor data corresponding to the current moment, it is determined whether the odor of the device under test has reached a stable state. If so, the third sensor data corresponding to the current moment is determined based on the second time series data corresponding to the current moment, and the reference data is updated to the third sensor data corresponding to the current moment; if not, the reference data is determined to be the third sensor data corresponding to the current moment.

[0121] Here, when judging whether the smell of the device under test has reached a stable state, two situations are mainly considered. One is that the smell inside the device under test has changed, but after the change, it gradually dissipates and returns to the stable state before the change. The other is that the smell inside the device under test has never changed, that is, it is always in a stable state. The stable state here can be understood as the state before the smell changes.

[0122] The following focuses on the first case. Considering that odor changes are usually a continuous process over a period of time, when the odor inside the device under test changes, the degree of odor change can be determined based on the odor conditions when the odor begins to change and the odor conditions at the current moment, so as to better perform fault monitoring.

[0123] In order to accurately determine the degree of change in the odor, the embodiment of the present invention uses the ratio of the reference data to the fourth sensor data corresponding to the current moment to determine whether the odor in the device under test has reached a stable state. It can be understood that the reference data can be used to characterize the odor situation when the odor begins to change. The fourth sensor data can be used to characterize the odor situation at the current moment. The embodiment of the present invention can determine whether the odor situation at the current moment has returned to the stable state before the odor change occurs by using the ratio of the reference data to the fourth sensor data at the current moment.

[0124] Specifically, if the ratio of the reference data and the fourth sensor data corresponding to the current moment does not exceed the first preset interval, it can be determined that the odor in the device to be tested has reached a stable state. If the ratio of the reference data and the fourth sensor data corresponding to the current moment exceeds the first preset interval, it can be determined that the odor in the device to be tested has not reached a stable state. Here, the upper limit value of the first preset interval is greater than 1, and the lower limit value of the first preset interval is less than 1. Exemplarily, the first preset interval can be expressed as [1-D, 1+D]. Wherein D represents a preset deviation value. The value of the preset deviation value can be determined according to actual conditions, and the embodiment of the present invention is not specifically limited here. Exemplarily, the value of D can be 0.001, 0.002 or 0.003, etc.

[0125] If the odor in the device under test has not reached a stable state, it is necessary to determine the third sensor data corresponding to the current moment with the reference data, and then calculate the odor characteristic data, so as to determine the degree of change of the odor from the time when the odor began to change to the current moment. If the odor in the device under test reaches a stable state, the third sensor data corresponding to the current moment can be determined based on the time series data corresponding to the current moment, and the reference data can be updated to the third sensor data corresponding to the current moment, so as to provide an odor reference basis for calculating the degree of change of the odor next time.

[0126] For the second case, if the odor in the device to be tested is always in a stable state, the third sensor data corresponding to the current moment can be determined based on the time series data corresponding to the current moment, and the reference data can be updated to the third sensor data corresponding to the current moment, so as to provide an odor reference basis for the next odor change.

[0127] Another application scenario is that after the smell in the device under test changes, it is impossible to restore to the stable state before the smell changes. If it takes a long time to restore to the stable state before the smell changes, it may be that the basic smell environment in the device under test has changed. To avoid misjudgment of this situation, the embodiment of the present invention introduces cumulative time to provide a new method for determining the third sensor data corresponding to the current moment. Figure 7 , as detailed below: Step 701: Based on the ratio of the reference data and the fourth sensing data corresponding to the current moment, determine whether the first condition and the second condition are met.

[0128] The first condition is that the odor of the device to be tested reaches a stable state, and the second condition is that the cumulative duration exceeds the preset reset duration. That is, when determining the third sensing data corresponding to the current moment, the embodiment of the present invention not only considers whether the odor reaches a stable state, but also considers whether the cumulative duration exceeds the preset reset duration.

[0129] According to the above embodiment, when the smell changes, the embodiment of the present invention always determines the reference data as the third sensor data corresponding to the current moment, and continues to use it to determine the degree of change of the smell between the time when the smell begins to change and the current moment.

[0130] In the embodiment of the present invention, the cumulative duration is introduced to characterize the usage duration of the reference data, that is, the duration from the moment when the odor begins to change to the current moment.

[0131] Step 702, if the first condition is met or the second condition is met, determine the third sensor data corresponding to the current moment according to the second time series data corresponding to the current moment, update the reference data to the third sensor data corresponding to the current moment, and clear the accumulated duration.

[0132] According to the above embodiment, if the odor in the device to be tested reaches a stable state, the third sensor data corresponding to the current moment is determined based on the second time series data corresponding to the current moment, and the reference data is updated to the third sensor data corresponding to the current moment, thereby providing a reference basis for the next odor change.

[0133] If the second condition is met, that is, the duration from the moment the odor begins to change to the current moment is too long, at this time, even if the odor in the device to be tested has not reached the stable state before the odor begins to change, the third sensor data corresponding to the current moment is still determined based on the second time series data corresponding to the current moment, and the reference data is updated to the third sensor data corresponding to the current moment.

[0134] The reason for this design is that when the odor changes and does not return to the stable state before the obvious change for a long time, it may be that the basic odor environment inside the device to be tested has changed. In order to avoid misjudgment due to changes in the basic odor environment, when the embodiment of the present invention determines that the cumulative time exceeds the preset reset time, it determines the third sensor data corresponding to the current moment based on the second time series data, and updates the reference data to the third sensor data corresponding to the current moment, which is equivalent to determining the current odor situation as a new stable state. By updating the reference data in the new stable state, a odor reference basis is provided for the next odor change.

[0135] It can be understood that the accumulated duration can be used to represent the retention duration of the reference data. Accordingly, after the reference data is updated, the accumulated duration needs to be cleared.

[0136] Step 703: If the first condition and the second condition are not satisfied, the reference data is determined to be the third sensing data corresponding to the current moment.

[0137] On the contrary, if the odor in the device to be tested has not returned to a stable state and the cumulative duration exceeds the preset reset duration, the reference data will not be updated and the reference data will be determined as the third sensor data corresponding to the current moment to determine the degree of odor change.

[0138] In addition to introducing the accumulated time, the embodiment of the present invention also needs to update the accumulated time in real time so that the entire process can be cyclically operated. To this end, for each type of odor sensing data, after determining the odor feature data corresponding to the odor sensing data at the current moment according to the ratio of the third sensing data to the fourth sensing data, the following is also included: For each type of odor sensing data, the cumulative duration corresponding to the odor sensing data is added to the unit duration to obtain an updated cumulative duration corresponding to the odor sensing data, wherein the unit duration is the time difference between two adjacent moments.

[0139] That is to say, for each type of odor sensing data at each moment, after calculating the odor characteristic data corresponding to that moment, it is necessary to update the cumulative duration according to the time difference between that moment and the next moment.

[0140] In addition, the accumulated time may be initialized at the start time, and the initialized accumulated time may be 0, so that the accumulated time may start to accumulate from 0.

[0141] The following is a detailed introduction to a method for determining the third sensing data based on the second time series data corresponding to the current moment.

[0142] When determining the third sensing data corresponding to the current moment based on the second time series data corresponding to the current moment, the embodiment of the present invention may first detect whether the accumulated duration is greater than the preset threshold duration. The preset threshold duration is less than the preset reset duration. Here, the embodiment of the present invention does not specifically limit the values ​​of the preset threshold duration and the preset reset duration. Exemplarily, the preset threshold duration may be 1 second, 2 seconds, or 3 seconds, etc. The preset reset duration may be 300 seconds, 400 seconds, or 500 seconds, etc.

[0143] If the accumulated duration corresponding to the current moment is greater than the preset threshold duration, the fourth sensing data corresponding to the current moment is determined as the third sensing data corresponding to the current moment; If the accumulated duration corresponding to the current moment is less than or equal to the preset threshold duration, the average value of the odor sensor data within the fifth preset time interval in the second time series data corresponding to the current moment is determined as the third sensor data corresponding to the current moment.

[0144] Regarding the situation where the odor in the device to be tested has reached stability at the current moment, by detecting whether the cumulative time is greater than the preset threshold time, it can be determined whether the reference data is used for too long. If the time is too long, it means that the odor has changed, and the change time has lasted for a long time, and then it has returned to a stable state before the change. At this time, if the third sensor data is determined directly based on the odor sensor data in the fifth preset time interval, the fifth preset time interval may happen to be the odor change interval, and the calculated third sensor data cannot accurately reflect the odor situation after reaching a stable state, resulting in misjudgment.

[0145] The embodiment of the present invention takes into account that after the odor reaches a stable state at the current moment, the third sensor data and the fourth sensor data are close. Therefore, the fourth sensor data corresponding to the current moment is directly updated to the third sensor data corresponding to the current moment, and the reference data is updated to the third sensor data corresponding to the current moment, so that the updated reference data can accurately reflect the odor situation after the odor reaches a stable state, and provide an odor reference basis for the next odor change.

[0146] If the accumulated duration is less than or equal to the preset threshold duration, it means that the odor has changed for a short time and has returned to a stable state. It can be simply understood that the odor has not changed significantly. At this time, the third sensor data corresponding to the current moment can be determined based on the odor sensor data in the fifth preset time interval corresponding to the current moment. That is, the average value of the odor sensor data in the fifth preset time interval in the second time series data corresponding to the current moment is determined as the third sensor data corresponding to the current moment.

[0147] To improve the accuracy of fault monitoring, the preset threshold time length may be set as small as possible. For example, the preset threshold time length may be 1 second, 2 seconds or 3 seconds.

[0148] Taking the unit time length as 1 second and the preset threshold time length as 1 second as an example, when the cumulative time length is greater than 1 second, it means that the reference data has been used for at least one moment, that is, the odor in the equipment to be tested has changed and has returned to the stable state before the change. At this time, in order to avoid misjudgment, the fourth sensor data corresponding to the current moment is directly used to determine the third sensor data corresponding to the current moment.

[0149] When the cumulative duration is less than or equal to 1, it means that the reference data has not been used, that is, the odor in the device to be tested has not changed significantly. At this time, the third sensor data corresponding to the current moment can be determined in real time based on the average value of the odor sensor data in the fifth preset time interval in the second time series data corresponding to the current moment, and the reference data can be updated to the third sensor data corresponding to the current moment accordingly.

[0150] For the situation where the cumulative duration exceeds the preset reset duration, at this time, it is possible to directly determine that the cumulative duration exceeds the preset threshold duration, and determine the third sensor data corresponding to the current moment in real time based on the average value of the odor sensor data in the fifth preset time interval in the second time series data corresponding to the current moment, and update the reference data to the third sensor data corresponding to the current moment accordingly.

[0151] The above embodiment mainly introduces the situation that the third sensing data is determined and the reference data is updated when the first condition or the second condition is satisfied. The following further introduces the situation that the first condition or the second condition is not satisfied.

[0152] If the first condition and the second condition are not met, it proves that the odor in the device under test has changed significantly and has not yet returned to the stable state before the change began, and the accumulated duration has not exceeded the preset reset duration. At this time, in order to avoid the phenomenon that the accumulated duration has reached the preset reset duration when the odor in the device under test is still in a continuous change, the embodiment of the present invention determines whether to reset the accumulated duration by detecting whether the odor situation at the current moment has reached a new stable state.

[0153] It is understandable that when the odor condition of the device under test is still in a state of continuous fluctuation at the current moment, in order to avoid the phenomenon that the cumulative duration exceeds the preset reset duration in this case, the cumulative duration can be forcibly cleared to avoid the phenomenon that the cumulative duration exceeds the preset reset duration in this case, thereby updating the reference data.

[0154] On the contrary, if the odor situation of the device under test is relatively stable at the current moment and no longer fluctuates continuously, it proves that the odor situation in the device under test is already in a new stable state. At this time, there is no need to reset the cumulative time. When the cumulative time reaches the preset reset time, the reference data can be directly updated to determine the odor situation in the new stable state, providing an odor reference basis for the next odor change.

[0155] Specifically, in some embodiments, if the first condition is not met and the second condition is not met, after the reference data is determined as the third sensor data corresponding to the current moment, the fifth sensor data and the sixth sensor data corresponding to the current moment can also be determined based on the second time series data corresponding to the current moment.

[0156] Here, the fifth sensing data is determined by the odor sensing data within the seventh preset time interval in the second time series data, and the sixth sensing data is determined by the odor sensing data within the eighth preset time interval in the second time series data.

[0157] Here, the fifth sensor data is the average value of the odor sensor data in the seventh preset time interval of the second time series data. The fourth and sixth sensor data are the average values ​​of the odor sensor data in the eighth preset time interval of the second time series data.

[0158] Among them, the eighth preset time interval is earlier than the seventh preset time interval; the current moment is in the seventh preset time interval. In essence, the fifth sensor data can be used to characterize the odor situation at the current moment. The sixth sensor data can characterize the odor situation before the current moment. The embodiment of the present invention determines whether the odor change situation at the current moment is stable based on the odor situation at the current moment and the odor situation between the current moment.

[0159] If the ratio of the fifth sensor data to the sixth sensor data exceeds the second preset interval, it proves that the odor change at the current moment has not stabilized and is still in continuous fluctuation. At this time, the cumulative duration will be cleared to zero to avoid the situation where the cumulative duration exceeds the preset reset time during the continuous fluctuation of the odor, thereby updating the reference data.

[0160] If the ratio of the fifth sensor data to the sixth sensor data does not exceed the second preset interval, it proves that the odor change at the current moment tends to be stable. At this time, there is no need to reset the cumulative time. When the cumulative time reaches the preset reset time, the reference data can be directly updated to determine the odor situation under the new stable state, providing an odor reference basis for the next odor change.

[0161] Here, the upper limit value of the second preset interval is greater than 1, and the lower limit value is less than 1.

[0162] Similar to the determination method of the first preset time interval to the sixth preset time interval, the embodiment of the present invention can determine the seventh preset time interval and the eighth preset time interval by setting parameters such as the length of the seventh preset time interval RgCVSQ, the length of the eighth preset time interval RgBVSQ, and the fourth time interval interval RgSI. The specific determination method is detailed in the above embodiment and will not be repeated here.

[0163] It is understandable that the third preset time interval length RgCVSQ and the fourth preset time interval length RgBVSQ are both integers greater than 1, and the second time interval interval RgSI is an integer greater than or equal to 0. The specific values ​​of the three can be determined according to actual conditions, and the embodiment of the present invention does not specifically limit this.

[0164] Exemplarily, the seventh preset time interval length RgCVSQ and the eighth preset time interval length RgBVSQ may both be 6 seconds, and the fourth time interval length RgSI may be 5 seconds.

[0165] Combine the following Figure 8 , a general introduction is given to the process of determining the third sensor data and the fourth sensor data corresponding to the current moment.

[0166] First, the system is initialized, mainly the accumulated time (RaLockCount) is initialized, and the data collection frequency of the sensor is set accordingly. Here, the data collection frequency can determine the time difference between two adjacent moments.

[0167] Secondly, obtain reference data (Rc). According to the average value of the odor sensor data in the sixth preset interval in the second time series data corresponding to the current moment, determine it as the fourth sensor data (Rg') corresponding to the current moment. The public expression is: Rg'=Avg(R[0-RgSQ],RgSQ).

[0168] Then, it is determined whether the accumulated time (RaLockCount) exceeds the preset reset time (RaResetCount) and whether the ratio of the reference data (Rc) to the fourth sensor data (Rg') exceeds the first preset interval. In the embodiment of the present invention, the first preset interval can be expressed as [1-D, 1+D].

[0169] One situation is: if the cumulative duration exceeds the preset reset duration, or the ratio of the reference data to the fourth sensor data corresponding to the current moment does not exceed the first preset interval, that is, RaLockCount>RaResetCount, or 1-D<= Rc÷Rg'<= 1 + D, then it is further determined whether the cumulative duration is greater than the preset threshold duration. In this embodiment of the present invention, the value of the preset threshold duration is 1.

[0170] If the accumulated duration is greater than the preset threshold duration, the fourth sensor data (Rg') corresponding to the current moment is updated to the third sensor data (Ra) corresponding to the current moment, and the reference data (Rc) is updated to the third sensor data (Ra) corresponding to the current moment.

[0171] If the cumulative duration is less than or equal to the preset threshold duration, the average value of the odor sensor data in the fifth preset time interval in the second time series data corresponding to the current moment is determined as the third sensor data (Ra) corresponding to the current moment, and the reference data (Rc) is updated to the third sensor data (Ra) corresponding to the current moment.

[0172] After updating the reference data (Rc), the accumulated duration (RaLockCount) is cleared.

[0173] According to the ratio of the third sensing data (Ra) and the fourth sensing data (Rg') corresponding to the current moment, the odor characteristic data (RaF) corresponding to the current moment is determined.

[0174] Another situation is: the accumulated duration does not exceed the preset reset duration, and the ratio of the reference data (Rc) to the fourth sensor data (Rg') corresponding to the current moment exceeds the first preset interval. At this time, the reference data (Rc) is determined as the third sensor data (Ra) corresponding to the current moment.

[0175] Then, the fifth sensor data (RgCV) corresponding to the current moment is determined according to the average value of the odor sensor data of the seventh preset time interval in the second time series data corresponding to the current moment. The public expression is: RgCV=Avg(R[0-RgCVSQ],RgCVSQ).

[0176] According to the average value of the odor sensor data of the eighth preset time interval in the time series data corresponding to the current moment, the sixth sensor data (RgBV) corresponding to the current moment is determined. The public expression is: RgBV=Avg(R[0-RgCVSQ-RgBVSQ-RgSI],RgBVSQ).

[0177] Next, the ratio of the fifth sensing data (RcBV) to the sixth sensing data (RgBV) is calculated to determine whether the odor situation in the device to be tested is stable at the current moment.

[0178] If the ratio of the fifth sensor data (RgCV) and the sixth sensor data (RgBV) exceeds the second preset interval, the cumulative duration clearing step is executed, and the odor characteristic data (RaF) is calculated based on the third sensor data (Ra) and the fourth sensor data (Rg') corresponding to the current moment.

[0179] If the ratio of the fifth sensor data (RgCV) to the sixth sensor data (RgBV) does not exceed the second preset interval, the cumulative time clearing step is not performed, and the odor characteristic data (RaF) is directly calculated based on the third sensor data (Ra) and the fourth sensor data (Rg') corresponding to the current moment. Here, the second preset interval can be expressed as [1-D, 1+D].

[0180] Finally, after determining the odor characteristic data (RaF) at the current moment, the cumulative duration (RaLockCount) is updated, and the step of determining the average value of the odor sensor data in the eighth preset interval in the second time series data corresponding to the current moment as the fourth sensor data corresponding to the current moment is restarted to calculate the odor characteristic data corresponding to the next moment.

[0181] Furthermore, in combination with the specific values ​​of each parameter, a specific example is provided to illustrate the method for determining the odor characteristic data. In this example, the data collection frequency is 1 second. Assuming that the current moment is the 15th second, the second time series data corresponding to the current moment can be expressed as: R1, R2, R3, R4, R5, R6, R7, R8, R9, R10, R11, R12, R13, R14, R15. The cumulative duration at the current moment is 1. The fifth preset time interval length RaSQ and the sixth preset time interval length RgSQ' are both 6 seconds, the seventh preset time interval length RgCVSQ and the eighth preset time interval length RgBVSQ are both 3 seconds, and the third time interval interval RaSI and the fourth time interval interval RgSI are both 1 second. The first preset interval and the second preset interval are both [0.998, 1.002]. The value of the preset threshold duration is 1. The value of the preset reset duration is 300 seconds.

[0182] First, the average value of the odor sensor data in the sixth preset time interval in the second time series data corresponding to the 15th second is determined as the fourth sensor data Rg' corresponding to the current moment. That is, the average value of R10, R11, R12, R13, R14, and R15 is determined as the fourth sensor data (Rg') corresponding to the 15th second.

[0183] Then, it is determined whether the accumulated time (RaLockCount) exceeds the preset reset time (RaResetCount) and whether the ratio of the reference data (Rc) to the fourth sensing data (Rg') exceeds the first preset interval [1-D, 1+D].

[0184] At this point, the accumulated duration has not exceeded the preset reset duration.

[0185] One situation is: if the ratio of the reference data (Rc) to the fourth sensor data (Rg') is within [0.998, 1.002], it is further determined whether the accumulated duration (RaLockCount) is greater than 1.

[0186] At this time, the cumulative duration (RaLockCount) is equal to 1, and the third sensor data (Ra) corresponding to the current moment is determined according to the average value of the odor sensor data in the fifth preset time interval, that is, the average value of R3, R4, R5, R6, R7, and R8 is determined as the third sensor data corresponding to the current moment, and the reference data Rc is updated to the third sensor data corresponding to the current moment.

[0187] After updating the reference data (Rc), the accumulated duration (RaLockCount) is cleared.

[0188] According to the ratio of the third sensing data (Ra) and the fourth sensing data (Rg') corresponding to the current moment, the odor characteristic data (RaF) corresponding to the current moment is determined.

[0189] Another situation is that the ratio of the reference data (Rc) to the fourth sensor data (Rg') corresponding to the current moment exceeds [0.998, 1.002]. At this time, the third sensor data corresponding to the 15th second still uses the reference data (Rc).

[0190] Subsequently, based on the average value of the odor sensor data in the seventh preset time interval (RgCVSQ) in the second time series data corresponding to the 15th second, the fifth sensor data (RgCV) corresponding to the current moment is determined, that is, the average value of R13, R14, and R15 is determined as the fifth sensor data RgCV.

[0191] According to the average value of the odor sensing data of the eighth preset time interval (RgBVSQ) in the time series data corresponding to the current moment, that is, the average value of R9, R10, and R11 is determined as the sixth sensing data (RgBV).

[0192] Next, determine whether the ratio of the fifth sensor data (RgCV) and the sixth sensor data (RgBV) exceeds [0.998, 1.002]. If so, execute the cumulative duration (RaLockCount) clearing step, and calculate the odor characteristic data (RaF) based on the third sensor data and the fourth sensor data corresponding to the 15th second.

[0193] If the ratio of the fifth sensor data (RgCV) to the sixth sensor data (RgBV) does not exceed [0.998, 1.002], the cumulative duration clearing step will not be performed, and the odor characteristic data (RaF) will be calculated directly based on the third sensor data and the fourth sensor data corresponding to the 15th second.

[0194] Finally, after determining the odor characteristic data at the 15th second, the cumulative duration (RaLockCount) is updated, and the step of determining the average value of the odor sensor data in the eighth preset interval in the second time series data corresponding to the current moment as the fourth sensor data corresponding to the current moment is jumped again to continue executing to calculate the odor characteristic data corresponding to the 16th second.

[0195] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0196] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0197] Fig. 9 The structure diagram of the smell-based abnormality reminder device provided by an embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows: like Fig. 9 As shown, the odor-based abnormality reminder device 9 includes: an acquisition module 91, a determination module 92 and a reminder module 93.

[0198] An acquisition module 91 is used to acquire at least one kind of odor sensing data inside the device to be tested; The determination module 92 is used to: For each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor characteristic data corresponding to the odor sensing data; the odor characteristic data is used to characterize the odor change in the device under test; respectively determining the data deviation of the odor characteristic data corresponding to each type of odor sensing data; The reminder module 93 is used to determine whether the operating state of the device under test is abnormal according to the data deviation, and send a reminder message when it is determined that the operating state is abnormal.

[0199] Optionally, the odor characteristic data corresponding to each type of odor sensing data includes: odor characteristic data corresponding to each type of odor sensing data at different moments; The determination module 92 is specifically used for: For each type of odor characteristic data, obtain the first time series data corresponding to the odor characteristic data at the current moment; the first time series data includes the odor characteristic data corresponding to the current moment and different moments before the current moment; Determine the first characteristic data and the second characteristic data corresponding to the current moment; the first characteristic data is determined by the odor characteristic data within the first preset time interval in the first time series data, and the second characteristic data is determined by the odor characteristic data within the second preset time interval in the first time series data; the first preset time interval is later than the second preset time interval; the current moment is within the first preset time interval; According to the ratio of the first characteristic data to the second characteristic data, the data deviation of the odor characteristic data at the current moment is determined.

[0200] Optionally, the reminder module 93 is specifically used for: According to the data deviation of various odor characteristic data, determine the data abnormality mark value corresponding to various odor characteristic data; The data anomaly mark values ​​corresponding to various odor characteristic data are accumulated, and based on the accumulated data anomaly mark values, it is determined whether the operating status of the device under test is abnormal.

[0201] Optionally, the reminder module 93 is specifically used for: When the accumulated data abnormality mark value is less than the first preset threshold value, it is determined that the operating state of the device under test is normal; When the accumulated data abnormality mark value is greater than or equal to the first preset threshold value and less than the second preset threshold value, it is determined that the operating state of the device under test is in a first-level abnormal state; When the accumulated data abnormality mark value is greater than or equal to the second preset threshold, it is determined that the operating state of the device under test is in a secondary abnormal state.

[0202] Optionally, the reminder module 93 is specifically used for: For each type of odor characteristic data, a data anomaly flag value of the odor characteristic data is determined according to a preset data interval in which the data deviation of the odor characteristic data is located; there are multiple preset data intervals, and different preset data intervals correspond to different data anomaly flag values; There is at least one pair of two adjacent target data intervals among the plurality of preset data intervals, and a difference between a first difference value corresponding to the two adjacent target data intervals and a second difference value corresponding to the remaining two adjacent data intervals is greater than a preset difference value; The first difference is the difference between the data anomaly mark values ​​corresponding to two adjacent target data intervals, and the second difference is the difference between the data anomaly mark values ​​corresponding to the remaining two adjacent data intervals.

[0203] Optionally, the reminder module 93 is specifically used for: Determine the sum of the data deviations of various odor characteristic data, and if the sum of the data deviations is less than a first preset deviation, determine that the operating state of the device under test is not abnormal; If the sum of the data deviations is greater than the first preset deviation, it is determined that an abnormality occurs in the operating state of the device under test.

[0204] Optionally, the determination module 92 is specifically configured to: For each type of odor sensing data, obtain the second time series data corresponding to the type of odor sensing data at the current moment; the second time series data includes the type of odor sensing data corresponding to the current moment and different moments before the current moment; Determine the first sensor data according to the average value of the odor sensor data within the third preset time interval in the second time series data corresponding to the current moment; The second sensor data is determined according to the average value of the odor sensor data within the fourth preset time interval in the second time series data corresponding to the current moment; the third preset time interval is earlier than the fourth preset time interval; the current moment is within the fourth preset time interval; According to the ratio of the first sensing data to the second sensing data, odor characteristic data corresponding to the odor sensing data at the current moment is determined.

[0205] Optionally, the determination module 92 is further configured to: The odor feature data corresponding to each type of odor sensing data is input into each pre-trained fault monitoring model to obtain the fault monitoring results output by each fault monitoring model; each fault monitoring model corresponds to a preset fault state; the fault monitoring model determines whether the device is in the corresponding preset fault state based on the odor feature data inside the device.

[0206] Optionally, the determination module 92 is specifically configured to: For each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor feature data corresponding to the odor sensing data, including: For each type of odor sensing data, obtain the second time series data corresponding to the type of odor sensing data at the current moment; the second time series data includes the type of odor sensing data corresponding to the current moment and different moments before the current moment; Determine the third sensor data and the fourth sensor data corresponding to the current moment; the third sensor data is determined by the odor sensor data within the fifth preset time interval in the second time series data, and the fourth sensor data is determined by the odor sensor data within the sixth preset time interval in the second time series data; the fifth preset time interval is earlier than the sixth preset time interval; the current moment is within the sixth preset time interval; According to the ratio of the third sensing data to the fourth sensing data, the odor characteristic data corresponding to the odor sensing data at the current moment is determined.

[0207] Optionally, the determination module 92 is specifically configured to: Determine the fourth sensor data corresponding to the current moment according to the average value of the odor sensor data within the sixth preset time interval in the second time series data corresponding to the current moment; The determination module 92 is specifically used for: Acquire reference data; the reference data is used to represent the odor sensing data when the odor in the device begins to change; Based on the ratio of the reference data and the fourth sensor data corresponding to the current moment, determine whether the odor of the equipment to be tested has reached a stable state. If so, determine the third sensor data corresponding to the current moment based on the second time series data corresponding to the current moment, and update the reference data to the third sensor data corresponding to the current moment; if not, determine the reference data to the third sensor data corresponding to the current moment.

[0208] Optionally, the determination module 92 is specifically configured to: Based on the ratio of the reference data and the fourth sensor data corresponding to the current moment, determine whether the first condition and the second condition are met, wherein the first condition is that the odor of the device to be tested reaches a stable state, and the second condition is that the accumulated time exceeds the preset reset time; If the first condition is met or the second condition is met, the third sensing data corresponding to the current moment is determined according to the second time series data corresponding to the current moment, the reference data is updated to the third sensing data corresponding to the current moment, and the accumulated duration is cleared; If the first condition is not satisfied and the second condition is not satisfied, the reference data is determined to be the third sensing data corresponding to the current moment; For each type of odor sensing data, after determining the odor characteristic data corresponding to the type of odor sensing data at the current moment according to the ratio of the third sensing data to the fourth sensing data, the method further includes: For each type of odor sensing data, the cumulative duration corresponding to the odor sensing data is added to the unit duration to obtain an updated cumulative duration corresponding to the odor sensing data, wherein the unit duration is the time difference between two adjacent moments.

[0209] Optionally, the determination module 92 is specifically configured to: Check whether the accumulated duration is greater than the preset threshold duration; the preset threshold duration is less than the preset reset duration; If the accumulated duration corresponding to the current moment is greater than the preset threshold duration, the fourth sensing data corresponding to the current moment is determined as the third sensing data corresponding to the current moment; If the accumulated duration corresponding to the current moment is less than or equal to the preset threshold duration, the average value of the odor sensor data within the fifth preset time interval in the second time series data corresponding to the current moment is determined as the third sensor data corresponding to the current moment.

[0210] Optionally, the determination module 92 is further configured to: According to the second time series data corresponding to the current moment, the fifth sensor data and the sixth sensor data corresponding to the current moment are determined; the fifth sensor data is determined by the odor sensor data within the seventh preset time interval in the second time series data, and the sixth sensor data is determined by the odor sensor data within the eighth preset time interval in the second time series data; the eighth preset time interval is earlier than the seventh preset time interval; the current moment is in the seventh preset time interval; If the ratio of the fifth sensor data to the sixth sensor data exceeds the second preset interval, the accumulated duration is cleared; the upper limit value of the second preset interval is greater than 1, and the lower limit value is less than 1.

[0211] Optionally, the odor sensing data is collected by a semiconductor gas sensor, an olfactory sensor or an odor sensor; the semiconductor gas sensor, the olfactory sensor or the odor sensor responds to at least one of ozone, carbon monoxide, hydrogen, nitrogen oxides, total volatile organic compounds, methane, carbon dioxide, 2-ethylhexanol, dioctyl terephthalate, benzene, hydrogen chloride, alkyl and alkenyl aromatic products, unsaturated hydrogen, aromatic hydrocarbon products, ammonia, hydrogen and hydrogen sulfide.

[0212] The real-time example of the device can be used to implement the above method embodiment, and the implementation effect of its technical principle is the same as that of the above method embodiment, which will not be repeated here.

[0213] Fig.10 Schematic diagram of an electronic device provided by an embodiment of the present invention. Fig.10 As shown, the electronic device 10 of this embodiment includes: a processor 1000 and a memory 1001. The memory 1001 stores a computer program 1002. When the processor 1000 executes the computer program 1002, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 1000 executes the computer program 1002, the functions of each module / unit in the above-mentioned device embodiments are implemented.

[0214] Exemplarily, the computer program 1002 may be divided into one or more modules / units, which are stored in the memory 1001 and executed by the processor 1000 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 1002 in the electronic device 100.

[0215] The electronic device 10 may include, but is not limited to, a processor 1000 and a memory 1001. Those skilled in the art will appreciate that Fig.10 It is only an example of the electronic device 10 and does not constitute a limitation of the electronic device 10. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 10 may also include input and output devices, network access devices, buses, etc.

[0216] The processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0217] The memory 101 may be an internal storage unit of the electronic device 10, such as a hard disk or memory of the electronic device 10. The memory 101 may also be an external storage device of the electronic device 10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 10. Further, the memory 1001 may also include both an internal storage unit of the electronic device 10 and an external storage device. The memory 101 is used to store the computer program 1002 and other programs and data required by the electronic device 10. The memory 1001 may also be used to temporarily store data that has been output or is to be output.

[0218] For the convenience and simplicity of description, only the division of the above functional modules / units is used as an example for illustration. In actual applications, the above functions can be assigned to different functional modules / units as needed. The above modules / units can be implemented in the form of hardware, software, or a combination of hardware and software.

[0219] The embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the methods in the above method embodiments are implemented.

[0220] The embodiment of the present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, the methods in the above method embodiments are implemented.

[0221] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. Computer readable media may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0222] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. If there is no special explanation and logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form a new embodiment according to their internal logical relationship.

[0223] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A smell-based abnormality reminder method, characterized in that: include: Acquiring at least one type of odor sensing data inside the device under test; For each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor characteristic data corresponding to the odor sensing data; the odor characteristic data is used to characterize the odor change in the device to be tested; respectively determining the data deviation of the odor characteristic data corresponding to each type of odor sensing data; According to the data deviation, it is determined whether the operating state of the device under test is abnormal, and when it is determined that the operating state is abnormal, a reminder message is sent.

2. The smell-based abnormal reminder method according to claim 1, characterized in that: The odor characteristic data corresponding to each type of odor sensing data includes: odor characteristic data corresponding to each type of odor sensing data at different times; The step of respectively determining the data deviation of the odor characteristic data corresponding to each type of odor sensing data comprises: For each type of odor characteristic data, obtain the first time series data corresponding to the odor characteristic data at the current moment; the first time series data includes the odor characteristic data corresponding to the current moment and different moments before the current moment; Determine the first characteristic data and the second characteristic data corresponding to the current moment; the first characteristic data is determined by the odor characteristic data within a first preset time interval in the first time series data, and the second characteristic data is determined by the odor characteristic data within a second preset time interval in the first time series data; the first preset time interval is later than the second preset time interval; the current moment is within the first preset time interval; According to the ratio of the first characteristic data to the second characteristic data, the data deviation of the odor characteristic data at the current moment is determined.

3. The odor-based abnormal reminder method according to claim 1 or 2, characterized in that: The step of determining whether the operating state of the device under test is abnormal according to the data deviation includes: According to the data deviation of various odor characteristic data, determine the data abnormality mark value corresponding to various odor characteristic data; The data anomaly mark values ​​corresponding to various odor characteristic data are accumulated, and whether the operating state of the device under test is abnormal is determined according to the accumulated data anomaly mark values.

4. The method for abnormality reminder based on smell according to claim 3, characterized in that: Determining whether the operating state of the device under test is abnormal according to the accumulated data abnormality mark value includes: When the accumulated data abnormality mark value is less than a first preset threshold, it is determined that the operating state of the device under test is normal; When the accumulated data abnormality mark value is greater than or equal to the first preset threshold value and less than the second preset threshold value, it is determined that the operating state of the device under test is in a first-level abnormal state; When the accumulated data abnormality mark value is greater than or equal to the second preset threshold, it is determined that the operating state of the device under test is in a secondary abnormal state.

5. The method for abnormality reminder based on smell according to claim 3, characterized in that: Determining the data abnormality mark value corresponding to each odor characteristic data according to the data deviation of each odor characteristic data includes: For each type of odor characteristic data, a data anomaly flag value of the odor characteristic data is determined according to a preset data interval in which the data deviation of the odor characteristic data is located; there are multiple preset data intervals, and different preset data intervals correspond to different data anomaly flag values; There is at least one pair of two adjacent target data intervals in the plurality of preset data intervals, and a difference between a first difference value corresponding to the two adjacent target data intervals and a second difference value corresponding to the remaining two adjacent data intervals is greater than a preset difference value; The first difference is the difference between the data anomaly mark values ​​corresponding to the two adjacent target data intervals, and the second difference is the difference between the data anomaly mark values ​​corresponding to the remaining two adjacent data intervals.

6. The odor-based abnormal reminder method according to claim 1 or 2, characterized in that: The step of determining whether the operating state of the device under test is abnormal according to the data deviation includes: Determine the sum of the data deviations of various odor characteristic data, and if the sum of the data deviations is less than a first preset deviation, determine that no abnormality occurs in the operating state of the device under test; If the sum of the data deviations is greater than a first preset deviation, it is determined that an abnormality occurs in the operating state of the device under test.

7. The odor-based abnormal reminder method according to claim 1 or 2, characterized in that: For each type of odor sensing data, extracting the data change characteristics of the odor sensing data to obtain odor characteristic data corresponding to the odor sensing data includes: For each type of odor sensing data, obtain the second time series data corresponding to the type of odor sensing data at the current moment; the second time series data includes the type of odor sensing data corresponding to the current moment and different moments before the current moment; Determine the first sensor data according to the average value of the odor sensor data within the third preset time interval in the second time series data corresponding to the current moment; Determine the second sensor data according to the average value of the odor sensor data in the fourth preset time interval in the second time series data corresponding to the current moment; the third preset time interval is earlier than the fourth preset time interval; the current moment is within the fourth preset time interval; According to the ratio of the first sensing data to the second sensing data, the odor characteristic data corresponding to the odor sensing data at the current moment is determined.

8. The smell-based abnormality reminder method according to claim 1, characterized in that: After extracting the data change characteristics of each type of odor sensing data and obtaining the odor characteristic data corresponding to the odor sensing data, the method further includes: The odor feature data corresponding to each type of odor sensing data is input into each pre-trained fault monitoring model to obtain the fault monitoring result output by each fault monitoring model; each fault monitoring model corresponds to a preset fault state; the fault monitoring model determines whether the device is in the corresponding preset fault state based on the odor feature data inside the device.

9. The smell-based abnormal reminder method according to claim 8, characterized in that: The odor characteristic data corresponding to each type of odor sensing data includes: odor characteristic data corresponding to each type of odor sensing data at different times; For each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor feature data corresponding to the odor sensing data, including: For each type of odor sensing data, obtain the second time series data corresponding to the type of odor sensing data at the current moment; the second time series data includes the type of odor sensing data corresponding to the current moment and different moments before the current moment; Determine the third sensor data and the fourth sensor data corresponding to the current moment; the third sensor data is determined by the odor sensor data within the fifth preset time interval in the second time series data, and the fourth sensor data is determined by the odor sensor data within the sixth preset time interval in the second time series data; the fifth preset time interval is earlier than the sixth preset time interval; the current moment is within the sixth preset time interval; According to the ratio of the third sensing data to the fourth sensing data, the odor characteristic data corresponding to the odor sensing data at the current moment is determined.

10. The smell-based abnormality reminder method according to claim 9, characterized in that: The determining of the fourth sensing data corresponding to the current moment includes: Determine the fourth sensor data corresponding to the current moment according to the average value of the odor sensor data within the sixth preset time interval in the second time series data corresponding to the current moment; The determining of the third sensing data corresponding to the current moment includes: Acquire reference data; the reference data is used to represent the odor sensing data when the odor in the device under test begins to change; Based on the ratio of the reference data and the fourth sensor data corresponding to the current moment, determine whether the odor of the equipment to be tested has reached a stable state. If so, determine the third sensor data corresponding to the current moment based on the second time series data corresponding to the current moment, and update the reference data to the third sensor data corresponding to the current moment; if not, determine the reference data as the third sensor data corresponding to the current moment.

11. The method for abnormality reminder based on smell according to claim 10, characterized in that: Based on the ratio of the reference data and the fourth sensor data corresponding to the current moment, determine whether the odor of the device to be tested has reached a stable state; if so, determine the third sensor data corresponding to the current moment according to the second time series data corresponding to the current moment, and update the reference data to the third sensor data corresponding to the current moment; If not, determining the reference data as the third sensing data corresponding to the current moment includes: Based on the ratio of the reference data and the fourth sensor data corresponding to the current moment, determine whether the first condition and the second condition are met, wherein the first condition is that the odor of the device to be tested reaches a stable state, and the second condition is that the accumulated time exceeds the preset reset time; If the first condition is met or the second condition is met, determining the third sensing data corresponding to the current moment according to the second time series data corresponding to the current moment, updating the reference data to the third sensing data corresponding to the current moment, and clearing the accumulated duration; If the first condition is not satisfied and the second condition is not satisfied, the reference data is determined as the third sensing data corresponding to the current moment; For each type of odor sensing data, after determining the odor characteristic data corresponding to the type of odor sensing data at the current moment according to the ratio of the third sensing data to the fourth sensing data, the method further includes: For each type of odor sensing data, the cumulative duration corresponding to the odor sensing data is added to the unit duration to obtain an updated cumulative duration corresponding to the odor sensing data, wherein the unit duration is the time difference between two adjacent moments.

12. The method for abnormality reminder based on smell according to claim 11, characterized in that: Determining third sensing data corresponding to the current moment according to the second time series data corresponding to the current moment includes: Detecting whether the accumulated duration is greater than a preset threshold duration; the preset threshold duration is less than the preset reset duration; If the accumulated duration corresponding to the current moment is greater than the preset threshold duration, the fourth sensing data corresponding to the current moment is determined as the third sensing data corresponding to the current moment; If the accumulated duration corresponding to the current moment is less than or equal to the preset threshold duration, the average value of the odor sensor data within the fifth preset time interval in the second time series data corresponding to the current moment is determined as the third sensor data corresponding to the current moment.

13. The odor-based abnormality reminder method according to claim 11 or 12, characterized in that: If the first condition is not satisfied and the second condition is not satisfied, after determining the reference data as the third sensing data corresponding to the current moment, the method further includes: According to the second time series data corresponding to the current moment, the fifth sensor data and the sixth sensor data corresponding to the current moment are determined; the fifth sensor data is determined by the odor sensor data within the seventh preset time interval in the second time series data, and the sixth sensor data is determined by the odor sensor data within the eighth preset time interval in the second time series data; the eighth preset time interval is earlier than the seventh preset time interval; the current moment is in the seventh preset time interval; If the ratio of the fifth sensor data to the sixth sensor data exceeds a second preset interval, the accumulated duration is cleared; an upper limit value of the second preset interval is greater than 1, and a lower limit value is less than 1.

14. The smell-based abnormality reminder method according to claim 1 or 2, characterized in that: The odor sensing data is collected by a semiconductor gas sensor, an olfactory sensor or an odor sensor; the semiconductor gas sensor, the olfactory sensor or the odor sensor responds to at least one of ozone, carbon monoxide, hydrogen, nitrogen oxides, total volatile organic compounds, methane, carbon dioxide, 2-ethylhexanol, dioctyl terephthalate, benzene, hydrogen chloride, alkyl and alkenyl aromatic products, unsaturated hydrogen, aromatic hydrocarbon products, ammonia, hydrogen and hydrogen sulfide.

15. An odor-based abnormality reminder device, characterized in that: include: An acquisition module, used to acquire at least one kind of odor sensing data inside the device to be tested; Identify modules for: For each type of odor sensing data, extract the data change characteristics of the odor sensing data to obtain odor characteristic data corresponding to the odor sensing data; the odor characteristic data is used to characterize the odor change in the device to be tested; respectively determining the data deviation of the odor characteristic data corresponding to each type of odor sensing data; The reminder module is used to determine whether the operating state of the device under test is abnormal according to the data deviation, and send a reminder message when it is determined that the operating state is abnormal.

16. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 14 when executing the computer program.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 14 is implemented.

18. A computer program product, characterized in that The method comprises a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 14.

Images