Fault detection sensor model generation method and device and nonvolatile storage medium

Abstract

The invention discloses a fault detection sensor model generation method and device and a nonvolatile storage medium. The method comprises the steps that multiple fault types of a target distribution transformer are acquired, and the multiple fault types are fault types of which the occurrence probability of the target distribution transformer is greater than a preset threshold value; determining a plurality of sensor types corresponding to the plurality of fault types; according to a plurality of preset performance characteristics, the plurality of sensor types are screened to obtain a plurality of final screening sensor types, and the plurality of performance characteristics represent working characteristics in the sensor application process; and integrating sensors corresponding to the plurality of final screening sensor types to obtain a fault detection sensor model for detecting the target distribution transformer. The technical problem that in the prior art, multiple faults possibly occurring in the distribution transformer cannot be detected at the same time through one detection device is solved.

Description

Technical Field

[0001] The present invention relates to the field of electrical equipment and measurement technology, and in particular to a method, device and non-volatile storage medium for generating a fault detection sensor model. Background Art

[0002] Power outages caused by distribution system problems account for the largest proportion of all power outage factors, up to 95%, and the power loss caused by the distribution network accounts for about 50% of the total power grid loss. In the entire distribution system, the distribution transformers are not only huge in number and involve a wide range of aspects, but more importantly, they are directly connected to power users. Therefore, whether the distribution transformers can operate normally will directly determine the safety of the distribution network and the reliability of power supply. In the long-term operation of the distribution network, the distribution transformers will inevitably be affected by natural or human factors, resulting in internal defects or failures, which will bring more serious hidden dangers to the safe and stable operation of the distribution system. The existing distribution transformer fault detection equipment is relatively single, and one fault detection device can only detect a certain type of fault in the distribution transformer. If you want to detect multiple possible faults of the distribution transformer at the same time, you need multiple different detection devices to detect them.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, and non-volatile storage medium for generating a fault detection sensor model, so as to at least solve the technical problem in the prior art that one detection device cannot be used to simultaneously detect multiple possible faults of a distribution transformer.

[0005] According to one aspect of an embodiment of the present invention, a method for generating a fault detection sensor model is provided, comprising: obtaining a plurality of fault types of a target distribution transformer, wherein the plurality of fault types are fault types whose occurrence probability of the target distribution transformer is greater than a predetermined threshold; determining a plurality of sensor types corresponding to the plurality of fault types, wherein sensors matching the plurality of sensor types are used to determine whether a fault of the corresponding fault type occurs in the target distribution transformer; screening the plurality of sensor types according to a plurality of pre-set performance characteristics to obtain a plurality of final screening sensor types, wherein the plurality of performance characteristics characterize the working characteristics of the sensor during the application process; integrating sensors corresponding to the plurality of final screening sensor types to obtain a fault detection sensor model for detecting the target distribution transformer.

[0006] Optionally, multiple fault types of the target distribution transformer are obtained, including: respectively obtaining historical fault data of sample distribution transformers, wherein the sample distribution transformer and the target distribution transformer are located in a predetermined area; and in the historical fault data, selecting fault types whose fault probability is greater than a predetermined threshold as multiple fault types.

[0007] Optionally, determining multiple sensor types corresponding to multiple fault types respectively includes: determining change conditions corresponding to each of the multiple fault types, wherein the change conditions corresponding to each of the multiple fault types are changes occurring in a sample distribution transformer that has a fault of the corresponding fault type, and the sample distribution transformer and the target distribution transformer are located in a predetermined area; based on the multiple change conditions, determining multiple sensor types corresponding to the multiple change conditions respectively.

[0008] Optionally, multiple sensor types are screened according to multiple pre-set performance characteristics to obtain multiple screened sensor types, including: preliminarily screening multiple sensor types according to a pre-set cost threshold to obtain multiple preliminary screening sensor types; screening multiple preliminary screening sensor types according to multiple performance characteristics to obtain multiple final screening sensor types.

[0009] Optionally, based on a preset cost threshold, a plurality of sensor types are preliminarily screened to obtain a plurality of initially screened sensor types, including: combining a plurality of sensor types according to a predetermined quantity to obtain a plurality of combinations; determining the respective costs of the plurality of combinations; screening out combinations whose costs do not exceed the cost threshold to obtain a plurality of groups of screened combinations, wherein the plurality of groups of screened combinations respectively include a plurality of initially screened sensor types.

[0010] Optionally, multiple preliminary screening sensor types are screened according to multiple performance characteristics to obtain multiple final screening sensor types, including: determining multiple performance data of any one of the multiple preliminary screening sensor types based on the multiple performance characteristics; determining the sum of the performance data of the multiple preliminary screening sensor types included in each of the multiple screened combinations; determining a target combination from the multiple screened combinations based on the sum of the performance data of the multiple preliminary screening sensor types included in each of the multiple screened combinations to obtain multiple groups of final screening sensor types.

[0011] According to another aspect of an embodiment of the present invention, a fault detection sensor model generation device is provided, including: an acquisition module, used to acquire multiple fault types of a target distribution transformer, wherein the multiple fault types are fault types whose occurrence probability of the target distribution transformer is greater than a predetermined threshold; a determination module, used to determine multiple sensor types corresponding to the multiple fault types, wherein sensors matching the multiple sensor types are used to determine whether faults of the corresponding fault types occur in the target distribution transformer; a screening module, used to screen the multiple sensor types according to multiple pre-set performance characteristics to obtain multiple final screening sensor types, wherein the multiple performance characteristics characterize the working characteristics of the sensors during application; an integration module, used to integrate sensors corresponding to the multiple final screening sensor types to obtain a fault detection sensor model for detecting the target distribution transformer.

[0012] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided. The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the fault detection sensor model generation methods.

[0013] According to another aspect of an embodiment of the present invention, there is provided an electronic device, comprising: one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the fault detection sensor model generation methods.

[0014] According to yet another aspect of the embodiments of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, any one of the above-mentioned fault detection sensor model generation methods is implemented.

[0015] In an embodiment of the present invention, multiple fault types of a target distribution transformer are obtained, wherein the multiple fault types are fault types whose occurrence probability of the target distribution transformer is greater than a predetermined threshold; multiple sensor types corresponding to the multiple fault types are determined, wherein sensors matching the multiple sensor types are used to determine whether faults of corresponding fault types occur in the target distribution transformer; multiple sensor types are screened according to multiple pre-set performance characteristics to obtain multiple final screening sensor types, wherein the multiple performance characteristics characterize the working characteristics of the sensors during application; sensors corresponding to the multiple final screening sensor types are integrated to obtain a fault detection sensor model for detecting the target distribution transformer, thereby achieving the purpose of generating a detection device that can simultaneously detect multiple faults that may occur in the distribution transformer, solving the technical problem in the prior art that one detection device cannot be used to simultaneously detect multiple faults that may occur in the distribution transformer, thereby achieving the technical effect of improving the efficiency of distribution transformer fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flow chart of a method for generating a fault detection sensor model provided by an embodiment of the present invention;

[0018] Figure 2 is a schematic diagram of an optional fault detection sensor model generation method provided according to an embodiment of the present invention;

[0019] Figure 3 is a schematic diagram of a fault detection sensor model generation device provided by an embodiment of the present invention;

[0020] Figure 4 is a schematic diagram of an electronic device provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0023] For the convenience of description, some nouns or terms involved in the embodiments of the present application are explained below:

[0024] Dimensionless: refers to processing data through certain mathematical methods so that the data is converted into a dimensionless unified form without changing its relative size relationship. In practical applications, dimensionless can help eliminate the dimensional differences between data, reduce the errors between data, and improve the comparability and interpretability of data. Common dimensionless methods include maximum-minimum standardization, Z-score standardization, and root mean square standardization. Among them, maximum-minimum standardization linearly transforms the data to the range of [0,1], Z-score standardization transforms the data into a normal distribution form with a mean of 0 and a standard deviation of 1, and root mean square standardization divides the data by the square root of the mean of the data. Dimensionless is widely used in data processing, data analysis, machine learning and other fields. It can improve the accuracy and efficiency of data processing, reduce the complexity of data analysis, and better understand the relationship and law between data.

[0025] An embodiment of the present invention provides an embodiment of a method for generating a fault detection sensor model. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 is a flow chart of a method for generating a fault detection sensor model according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0027] Step S102: acquiring multiple fault types of the target distribution transformer, wherein the multiple fault types are fault types of which the occurrence probability of the target distribution transformer is greater than a predetermined threshold.

[0028] In this step, the possible faults of the distribution transformer include but are not limited to: (1) Excessive temperature rise: excessive temperature due to poor heat dissipation or cooling system failure. (2) Overload: If the transformer works for a long time under a load exceeding the rated load, it will overheat and be damaged. (3) Insulation damage: Aging or moisture of the insulation material will cause the insulation strength to decrease, and it is easy to break down. (4) Oil leakage: Leakage of insulating oil inside the transformer will affect the insulation performance and cause faults. (5) Failure of short-circuit protection: Failure of the short-circuit protection device will cause the transformer to be unable to cut off the power supply in time in the event of a short circuit, causing serious damage. (6) Grounding fault: A grounding fault in the transformer casing or grounding line will affect the safety performance. From the various possible faults of the distribution transformer, select the fault type with a probability exceeding a predetermined threshold. For example, if the predetermined threshold is 5%, then select the fault type with a probability exceeding 5% from the various possible faults of the distribution transformer. The predetermined threshold can be determined according to actual needs.

[0029] In an optional embodiment, historical fault data of sample distribution transformers are respectively obtained, wherein the sample distribution transformers and the target distribution transformers are located in a predetermined area; and in the historical fault data, fault types having a fault probability greater than a predetermined threshold are selected as the multiple fault types.

[0030] Optionally, the historical fault data of the distribution transformer is usually recorded in the database or archive of the distribution system, and some power companies may also save this data in a specific software system for data analysis and fault prediction. The historical fault data of the sample distribution transformer is obtained from these databases or archives, and the fault type with a probability of occurrence greater than a predetermined threshold is selected from these historical fault data. The distribution transformer fault detection model generated by this method is mainly to detect faults with a high probability of occurrence in the distribution transformer and realize efficient and comprehensive distribution transformer fault detection. For example, the predetermined threshold is 10%, that is, the fault type with a probability of occurrence greater than 10% is selected. Assume that the probability of occurrence of fault type A in the historical fault data is 15%, and the probability of occurrence of fault type B is 5%. Then fault type A is greater than the predetermined threshold and belongs to the selected fault type, while fault type B is less than the predetermined threshold and does not belong to the selected fault type.

[0031] Step S104, determining a plurality of sensor types corresponding to a plurality of fault types respectively, wherein sensors matching the plurality of sensor types are used to determine whether a fault of a corresponding fault type occurs in the target distribution transformer.

[0032] In this step, after determining multiple fault types, multiple sensor types corresponding to the fault types are selected, and each type of sensor is responsible for detecting a fault in the distribution transformer. For example, an insulation resistance sensor is selected to detect the insulation damage fault that is difficult to occur in the distribution transformer. Once the insulation resistance drops to a dangerous level, it can be determined that the distribution transformer has an insulation fault. A pressure sensor or a liquid level sensor can be selected to detect the oil leakage fault of the transformer. If the oil pressure drops or the liquid level drops below a predetermined value, it can be determined that the transformer has an oil leakage fault. A current sensor is selected to detect the short circuit fault of the transformer. If the current increases abnormally or is suddenly interrupted, it can be determined that the distribution transformer has a short circuit fault.

[0033] In an optional embodiment, the change conditions corresponding to each of the multiple fault types are determined, wherein the change conditions corresponding to each of the multiple fault types are changes occurring in a sample distribution transformer that has a fault of the corresponding fault type, and the sample distribution transformer and the target distribution transformer are located in a predetermined area; based on the multiple change conditions, multiple sensor types corresponding to the multiple change conditions are determined.

[0034] Optionally, it is necessary to determine the changes corresponding to different fault types. These changes refer to the specific changes that will occur when a certain fault occurs in the sample distribution transformer. For example, assuming that the normal temperature range of the distribution transformer is 0-40°C, when the temperature of the distribution transformer suddenly rises and exceeds 40°C, it proves that the distribution transformer has an overheating fault. A temperature sensor should be selected to detect the overheating fault. Similarly, different types of sensors are determined based on the changes in the distribution transformer when each fault occurs. Each fault has a corresponding type of sensor for detection, which can effectively improve the accuracy and efficiency of fault detection.

[0035] Step S106, screening multiple sensor types according to multiple pre-set performance characteristics to obtain multiple final screened sensor types, wherein the multiple performance characteristics represent the working characteristics of the sensor during application.

[0036] In this step, multiple performance characteristics are preset, and these performance characteristics are determined according to the working characteristics of the sensor during the application process, including but not limited to the field application difficulty, sensitivity, detection range, response time, anti-interference ability, etc. of various types of sensors. According to these performance indicators, multiple sensor types are screened, and multiple final screened sensor types are selected and finally integrated into a fault detection sensor model.

[0037] In an optional embodiment, a plurality of sensor types are preliminarily screened according to a preset cost threshold to obtain a plurality of preliminary screening sensor types; and the plurality of preliminary screening sensor types are screened according to a plurality of performance characteristics to obtain a plurality of final screening sensor types.

[0038] Optionally, after selecting multiple sensor types corresponding to multiple fault types, it is necessary to perform preliminary screening and final screening on the multiple sensor types in turn to determine the sensor type that can be finally used for the integrated fault detection sensor model. The basis for preliminary screening is a pre-set cost threshold, which can be determined based on the average cost of the sample distribution transformer. Assuming that the average cost of the sample distribution transformer is 10,000 yuan, the cost threshold can be no more than one-tenth of the average cost of the distribution transformer, that is, the cost threshold is 1,000 yuan. The basis for final screening is multiple performance characteristics, such as field application difficulty, sensitivity, detection range, response time, anti-interference ability, etc. After preliminary screening of multiple sensor types based on the pre-set cost threshold, multiple preliminary screening sensor types are obtained. On the basis of multiple preliminary screening sensor types, multiple preliminary screening sensor types are finally screened based on multiple performance characteristics to obtain multiple final screening sensor types.

[0039] In an optional embodiment, multiple sensor types are combined according to a predetermined number to obtain multiple combinations; the cost of each of the multiple combinations is determined; and the combinations whose costs do not exceed a cost threshold are screened out to obtain multiple groups of screened combinations, wherein the multiple groups of screened combinations respectively include multiple preliminary screening sensor types.

[0040] Optionally, multiple sensor types are combined according to a predetermined number to obtain multiple combinations. Assuming the predetermined number is 5, the multiple types of sensors are: acoustic wave sensor, temperature sensor, humidity sensor, liquid level sensor, current sensor, voltage sensor, gas sensor, a total of 7 types of sensors. Then freely combine these 7 types of sensors, according to the permutation and combination formula, there are a total of 21 combinations. Calculate the total cost of the five types of sensors included in the 21 combinations, and select the combination whose total cost does not exceed the cost threshold. The sensor types included in these combinations whose total cost does not exceed the cost threshold are multiple preliminary screening sensor types.

[0041] In an optional embodiment, based on multiple performance characteristics, multiple performance data of any one of multiple preliminary screening sensor types are determined; the sum of the performance data of the multiple preliminary screening sensor types included in each of the multiple groups of screened combinations is determined; based on the sum of the performance data of the multiple preliminary screening sensor types included in each of the multiple groups of screened combinations, a target combination is determined from the multiple groups of screened combinations to obtain multiple groups of final screening sensor types.

[0042] Optionally, the multiple initial screening sensor types included in the multiple combinations are set to be acoustic sensor, temperature sensor, humidity sensor, liquid level sensor, current sensor, and voltage sensor, a total of six. The multiple performance characteristics are set to be: field application difficulty, sensitivity, detection range, response time, and anti-interference ability, a total of five.

[0043] The six types of preliminary screening sensors were dimensionlessized using five performance characteristics. For the performance characteristic of sensitivity, the higher the better, that is, the performance characteristic of maximum value tendency, the maximum value of the performance characteristic should be used as the standard for dimensionlessization. The calculation formula is as follows:

[0044]

[0045] Among them, x ij ' represents the dimensionless value of the i-th type of sensor according to the j-th performance characteristic, x ij Indicates the performance value of the sensor to be evaluated, {x 1j 、x 2j 、x 3j 、x 4j , …, x nj} maxIndicates selecting the maximum value from the set of values ​​of this performance characteristic.

[0046] For the performance characteristic of response time, the lower the better, that is, the performance characteristic with a minimum trend, it is necessary to make it dimensionless based on the minimum value of the performance characteristic. The calculation formula is as follows:

[0047]

[0048] At this time, x ij ' represents the dimensionless value of the i-th type of sensor according to the j-th performance characteristic, x ij Indicates the performance value of the sensor to be evaluated, {x 1j 、x 2j 、x 3j 、x 4j , …, x nj} min Indicates selecting the minimum value from the set of values ​​of this performance characteristic.

[0049] If the minimum value is used as the benchmark, the dimensionless value obtained will be greater than 1, and the final value of this scheme is 1 as the maximum value, so at this time, these values ​​must be normalized in the same direction to obtain the dimensionless values ​​of the performance characteristics of each type of preliminary screened sensor that have a tendency towards the minimum value.

[0050]

[0051] x ij ' represents the value obtained by dimensionless conversion based on the minimum value of the performance characteristic, x ij " indicates that x ij 'The value obtained after normalization, x ij ' is greater than 1.

[0052] The dimensionless values ​​of the five performance characteristics of each type of preliminary screening sensor are summed up to obtain the dimensionless total value of each type of preliminary screening sensor.

[0053] The dimensionless total values ​​of the five preliminary screening sensor types included in each of the multiple groups of screened combinations are sorted in descending order, and multiple sensor types in the order before the second threshold after the multiple groups of screening are determined to obtain multiple final screening combinations. The multiple sensor types included in each final screening combination are the multiple final screening sensor types.

[0054] Step S108, integrating sensors corresponding to the multiple final screening sensor types to obtain a fault detection sensor model for detecting the target distribution transformer.

[0055] In this step, the multiple final screening sensor types included in each of the multiple groups of screened combinations are integrated into a comprehensive sensor. First, a suitable hardware platform is selected according to the sensor type, such as Arduino, etc., and multiple types of final screening sensors are connected to the hardware platform to ensure that they can work properly. Secondly, a program is written to obtain data from each final screening sensor, and the data is processed and analyzed to obtain a fault detection sensor model. Finally, the fault detection sensor model is tested to test the detection effect of the fault detection sensor model. When the expected detection effect is obtained, researchers can manufacture corresponding fault detection sensors based on the fault detection sensor model and apply them in real life to detect various possible faults of distribution transformers.

[0056] Through the above, multiple fault types of the target distribution transformer are obtained, wherein the multiple fault types are fault types whose occurrence probability of the target distribution transformer is greater than a predetermined threshold; multiple sensor types corresponding to the multiple fault types are determined, wherein sensors matching the multiple sensor types are used to determine whether the target distribution transformer has a fault of the corresponding fault type; multiple sensor types are screened according to multiple pre-set performance characteristics to obtain multiple final screening sensor types, wherein multiple performance characteristics characterize the working characteristics of the sensor during the application process; sensors corresponding to the multiple final screening sensor types are integrated to obtain a fault detection sensor model for detecting the target distribution transformer. The purpose of generating a detection device that can simultaneously detect multiple faults that may occur in the distribution transformer is achieved, and the technical problem that it is impossible to use one detection device to simultaneously detect multiple faults that may occur in the distribution transformer in the prior art is solved, thereby achieving the technical effect of improving the efficiency of distribution transformer fault detection.

[0057] Based on the above embodiments and optional embodiments, the present invention proposes an optional implementation mode, such as Figure 2 As shown, the scheme includes the following steps:

[0058] Step S1, respectively obtaining historical fault data of sample distribution transformers, wherein the sample distribution transformers and the target distribution transformers are located in a predetermined area; in the historical fault data, selecting fault types with a fault probability greater than a predetermined threshold as multiple fault types.

[0059] Optionally, generally speaking, the service life of a distribution transformer is about 20 years, so the historical fault data in this application refers to the statistics of faults that occurred in the sample distribution transformers selected in the predetermined area in the past 20 years. Since it is impossible for the distribution transformer detection equipment to detect all faults that occur in the distribution transformer at the same time, in order to ensure that the distribution transformer detection equipment can play the maximum role, the distribution transformer detection equipment is used to detect the most common faults of the distribution transformer. The historical fault data of the sample distribution transformers in the predetermined area are screened to screen out the fault types with a probability of occurrence greater than a predetermined threshold. For example, the predetermined threshold is set to 10%, that is, the fault types with a probability of occurrence exceeding 10% are screened out in the historical fault data.

[0060] Step S2, determining the change conditions corresponding to each of the multiple fault types, wherein the change conditions corresponding to each of the multiple fault types are changes occurring in a sample distribution transformer that has a fault of the corresponding fault type, and the sample distribution transformer and the target distribution transformer are located in a predetermined area; based on the multiple change conditions, determining multiple sensor types corresponding to the multiple change conditions, respectively.

[0061] Optionally, when a distribution transformer fails, the distribution transformer will change. According to the different changes of the distribution transformer, multiple types of sensors for detecting different changes are determined. For example, when a sound fault occurs in the distribution transformer, the local discharge sound signal emitted by the distribution transformer gradually transitions from ultrasound to audible sound, so a sound sensor can be selected to detect the sound changes in the distribution transformer. When an oil leakage fault occurs in the distribution transformer, the oil pressure drops, and a pressure sensor can be selected to detect the oil pressure change of the distribution transformer. Figure 2 As shown, according to the various changes of the distribution transformer when it fails, the various types of sensors determined are: ultra-high frequency sensor, high frequency CT sensor, ultrasonic sensor, audible sound sensor, vibration sensor, temperature sensor, magnetic field sensor, and oil-soluble gas sensor, a total of eight types.

[0062] Step S3, combining multiple sensor types according to a predetermined number to obtain multiple combinations; determining the costs of each of the multiple combinations; screening out combinations whose costs do not exceed a cost threshold to obtain multiple groups of screened combinations, wherein the multiple groups of screened combinations respectively include multiple preliminary screening sensor types.

[0063] Optionally, multiple sensor types are combined according to a predetermined number. Assume that the predetermined number is 8 and the cost threshold is 1,000 yuan. Figure 2As shown, there is only one combination of eight types of sensors. The total cost of the ultra-high frequency sensor, high-frequency CT sensor, ultrasonic sensor, audible sound sensor, vibration sensor, temperature sensor, magnetic field sensor, and oil-soluble gas sensor included in the combination is calculated. If the total cost of the eight sensors does not exceed 1,000 yuan, the eight sensors included in the combination are multiple initial screening sensor types. If the total cost of the eight sensors exceeds 1,000 yuan, the combination does not meet the initial screening conditions.

[0064] Step S4, based on multiple performance characteristics, determine multiple performance data of any one sensor type among multiple preliminary screening sensor types; determine the sum of the performance data of multiple preliminary screening sensor types included in multiple groups of screened combinations; according to the sum of the performance data of multiple preliminary screening sensor types included in multiple groups of screened combinations, determine the target combination among the multiple groups of screened combinations to obtain multiple groups of final screening sensor types.

[0065] Optional, such as Figure 2 As shown in the figure, multiple performance characteristics can be set as design cost, field application difficulty, sensitivity, detection range, response time, and anti-interference ability. Among them, the design cost is used to measure whether the structural design of the fault detection sensor model is reasonable. Field application difficulty refers to the difficulty of installing and debugging the sensor in the actual application scenario, including installation location selection, calibration and debugging, etc. Sensitivity refers to the sensitivity of the sensor to the change of the measured physical quantity, that is, the minimum change that the sensor can detect. The detection range refers to the range of physical quantities that the sensor can detect, that is, the range between the maximum and minimum measurement values ​​of the physical quantity. The response time refers to the time interval from the sensor receiving the input signal to the output of the detection result, that is, the reaction speed of the sensor. Anti-interference ability refers to the ability of the sensor to maintain stable performance when subjected to external interference, that is, the sensor's resistance to interference signals.

[0066] The eight types of sensors are dimensionless according to the six performance characteristics. The specific steps are as follows:

[0067] The six performance indicators are classified, among which the three performance characteristics of design cost, field application difficulty and response time are performance characteristics tending towards minimum values ​​and should be dimensionless based on the minimum values ​​of the performance characteristics.

[0068] The calculation formula is as follows:

[0069]

[0070] x ij' represents the dimensionless value of the i-th type of sensor according to the j-th performance characteristic, i represents the type of sensor, j represents the performance characteristic, and in this formula, j can represent the design cost, field application difficulty, or response time. ij Indicates the performance value of the sensor to be evaluated, {x 1j 、x 2j 、x 3j 、x 4j , …, x nj} min Indicates selecting the minimum value from the set of values ​​of this performance characteristic.

[0071] If the minimum value is used as the benchmark, the dimensionless value obtained will be greater than 1, and the final value of this scheme is 1 as the maximum value, so at this time, these values ​​must be normalized in the same direction to obtain the dimensionless values ​​of the performance characteristics of each type of preliminary screened sensor after the three minimum value trends.

[0072]

[0073] x ij ' represents the value obtained by dimensionless conversion based on the minimum value of the performance characteristic, x ij " indicates that x ij 'The value obtained after normalization, x ij ' is greater than 1.

[0074] Sensitivity, detection range, and anti-interference ability are the three performance characteristics that tend to be maximum values, and should be dimensionless based on the maximum value of the performance characteristics. The calculation formula is as follows:

[0075]

[0076] At this time, x ij ' represents the dimensionless value of the i-th type of sensor according to the j-th performance characteristic, i represents the type of sensor, j represents the performance characteristic, and in this formula, j can represent the sensitivity, detection range or anti-interference ability. ij Indicates the performance value of the sensor to be evaluated, {x 1j 、x 2j 、x 3j 、x 4j , …, x nj} max Indicates selecting the maximum value from the set of values ​​of this performance characteristic.

[0077] The dimensionless values ​​of each sensor according to the six performance characteristics are summed to obtain the sum of the performance data of each sensor. The sum of the performance data of each sensor is sorted from large to small, and the sensor type before the second threshold is selected. For example, if the second threshold is 5, five sensor types are selected as the final screening sensor types.

[0078] Step S5, integrating sensors corresponding to the multiple final screening sensor types to obtain a fault detection sensor model for detecting the target distribution transformer.

[0079] Optionally, the steps for integrating sensors corresponding to multiple final screening sensor types are as follows: first, determine the relationship between multiple final screening sensors, including whether there is mutual influence or data fusion is required, and then design a suitable data fusion algorithm based on the relationship and requirements between sensors to integrate and analyze the data of each sensor. Third, develop a sensor integration system based on the designed algorithm and requirements to connect the sensors together and realize data collection, processing and output. Finally, test and verify the integrated sensor system.

[0080] The above-mentioned optional implementation manner achieves at least the following effects: the present application can select the appropriate sensor type through two screenings, generate an efficient fault detection sensor model, and achieve the technical effect of using one device to simultaneously detect multiple possible faults of the distribution transformer, thereby improving the accuracy and efficiency of distribution transformer fault detection.

[0081] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0082] In this embodiment, a fault detection sensor model generation device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the terms "module" and "device" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0083] According to an embodiment of the present invention, there is also provided an embodiment of a device for implementing a method for generating a fault detection sensor model. Figure 3 A schematic diagram of a fault detection sensor model generation device according to an embodiment of the present invention is shown in FIG. Figure 3As shown, the above-mentioned fault detection sensor model generation device includes an acquisition module 31, a determination module 32, a screening module 33, and an integration module 34. The device is described below.

[0084] The acquisition module 31 is used to acquire multiple fault types of the target distribution transformer, wherein the multiple fault types are fault types of which the occurrence probability of the target distribution transformer is greater than a predetermined threshold.

[0085] The determination module 32, connected with the acquisition module 31, is used to determine a plurality of sensor types corresponding to a plurality of fault types, wherein sensors matching the plurality of sensor types are used to determine whether a fault of a corresponding fault type occurs in the target distribution transformer.

[0086] The screening module 33 is connected to the determination module 32 and is used to screen a plurality of sensor types according to a plurality of pre-set performance characteristics to obtain a plurality of final screening sensor types, wherein the plurality of performance characteristics characterize the working characteristics of the sensor during application.

[0087] The integration module 34 is connected to the screening module 33 and is used to integrate sensors corresponding to a plurality of final screening sensor types to obtain a fault detection sensor model for detecting a target distribution transformer.

[0088] In a fault detection sensor model generation device provided by an embodiment of the present invention, an acquisition module is set to acquire multiple fault types of a target distribution transformer, wherein the multiple fault types are fault types whose occurrence probability of the target distribution transformer is greater than a predetermined threshold; a determination module is used to determine multiple sensor types corresponding to the multiple fault types, wherein sensors matching the multiple sensor types are used to determine whether the target distribution transformer has a fault of the corresponding fault type; a screening module is used to screen the multiple sensor types according to multiple pre-set performance characteristics to obtain multiple final screening sensor types, wherein the multiple performance characteristics characterize the working characteristics of the sensor during the application process; an integration module is used to integrate sensors corresponding to the multiple final screening sensor types to obtain a fault detection sensor model for detecting the target distribution transformer. The purpose of generating a detection device that can simultaneously detect multiple faults occurring in a distribution transformer is achieved, and the technical problem that one detection device cannot be used to simultaneously detect multiple faults that may occur in a distribution transformer in the prior art is solved. The technical effect of improving the efficiency of fault detection of distribution transformers is thereby achieved.

[0089] The purpose is achieved, and the technical problem that one detection device cannot be used to simultaneously detect multiple faults that may occur in the distribution transformer in the prior art is solved, thereby achieving the technical effect.

[0090] It should be noted that the above modules can be implemented by software or hardware. For example, for the latter, it can be implemented in the following ways: the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0091] It should be noted that the acquisition module 31, the determination module 32, the screening module 33, and the integration module 34 correspond to steps S102 to S108 in the embodiment, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the modules as part of the device can be run in a computer terminal.

[0092] It should be noted that the optional or preferred implementation of this embodiment can refer to the relevant description in the embodiment, which will not be repeated here.

[0093] The above-mentioned fault detection sensor model generation device may also include a processor and a memory. The acquisition module 31, the determination module 32, the screening module 33, the integration module 34, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0094] The processor includes a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels. The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0095] An embodiment of the present invention provides a non-volatile storage medium on which a program is stored. When the program is executed by a processor, a method for generating a fault detection sensor model is implemented.

[0096] like Figure 4 It is shown that an embodiment of the present invention provides an electronic device, the electronic device 10 includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented: the memory is used to store a computer program, wherein, when the computer program is executed by the processor, the processor implements the above-mentioned fault detection sensor model generation method. The device in this article can be a server, a PC, etc.

[0097] The present invention also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: computer instructions are executed by a processor to perform the above-mentioned fault detection sensor model generation method.

[0098] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0100] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0102] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0103] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0104] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0105] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0106] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0107] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A method for generating a fault detection sensor model, characterized in that: include: Acquire multiple fault types of a target distribution transformer, wherein the multiple fault types are fault types whose occurrence probability of the target distribution transformer is greater than a predetermined threshold; Determine a plurality of sensor types corresponding to the plurality of fault types respectively, wherein sensors matching the plurality of sensor types are used to determine whether a fault of a corresponding fault type occurs in the target distribution transformer; Screening the multiple sensor types according to a plurality of pre-set performance characteristics to obtain a plurality of final screened sensor types, wherein the plurality of performance characteristics characterize working characteristics of the sensors during application; Sensors corresponding to the multiple final screening sensor types are integrated to obtain a fault detection sensor model for detecting the target distribution transformer.

2. The method according to claim 1, characterized in that The method of obtaining multiple fault types of the target distribution transformer includes: Respectively acquiring historical fault data of sample distribution transformers, wherein the sample distribution transformers and the target distribution transformers are located in a predetermined area; In the historical fault data, fault types whose fault probabilities are greater than a predetermined threshold are selected as the multiple fault types.

3. The method according to claim 1, characterized in that The determining of a plurality of sensor types respectively corresponding to the plurality of fault types comprises: Determining the change conditions corresponding to each of the multiple fault types, wherein the change conditions corresponding to each of the multiple fault types are changes occurring in a sample distribution transformer having a fault of the corresponding fault type, and the sample distribution transformer and the target distribution transformer are located in a predetermined area; According to the multiple change situations, multiple sensor types respectively corresponding to the multiple change situations are determined.

4. The method according to claim 1, characterized in that: The multiple sensor types are screened according to the preset multiple performance characteristics to obtain the screened multiple sensor types, including: Preliminarily screening the multiple sensor types according to a preset cost threshold to obtain multiple preliminarily screened sensor types; The multiple preliminary screening sensor types are screened according to the multiple performance characteristics to obtain the multiple final screening sensor types.

5. The method according to claim 4, characterized in that According to a preset cost threshold, the multiple sensor types are preliminarily screened to obtain multiple preliminarily screened sensor types, including: Combining the plurality of sensor types according to a predetermined number to obtain a plurality of combinations; determining a cost for each of the plurality of combinations; Combinations whose costs do not exceed the cost threshold are screened out to obtain multiple groups of screened combinations, wherein the multiple groups of screened combinations respectively include the multiple initial screening sensor types.

6. The method according to claim 5, characterized in that The multiple preliminary screening sensor types are screened according to the multiple performance characteristics to obtain the multiple final screening sensor types, including: Determining, based on the plurality of performance characteristics, a plurality of performance data of any one of the plurality of primary screening sensor types; Determining the sum of performance data of a plurality of initially screened sensor types included in each of the plurality of groups of screened combinations; According to the sum of the performance data of the multiple preliminary screening sensor types respectively included in the multiple groups of screened combinations, a target combination is determined from the multiple groups of screened combinations to obtain multiple groups of the multiple final screening sensor types.

7. A fault detection sensor model generation device, characterized in that: include: An acquisition module, used for acquiring multiple fault types of a target distribution transformer, wherein the multiple fault types are fault types of which the occurrence probability of the target distribution transformer is greater than a predetermined threshold; A determination module, used to determine a plurality of sensor types corresponding to the plurality of fault types, respectively, wherein sensors matching the plurality of sensor types are used to determine whether a fault of a corresponding fault type occurs in the target distribution transformer; A screening module, used to screen the multiple sensor types according to a plurality of pre-set performance characteristics to obtain a plurality of final screened sensor types, wherein the plurality of performance characteristics represent working characteristics of the sensor during application; The integration module is used to integrate sensors corresponding to the multiple final screening sensor types to obtain a fault detection sensor model for detecting the target distribution transformer.

8. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the fault detection sensor model generation method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: One or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the fault detection sensor model generation method described in any one of claims 1 to 6.

10. A computer program product comprising computer instructions, characterized in that: The computer instructions are executed by a processor to implement the fault detection sensor model generation method described in any one of claims 1 to 6.

Images