LED lighting lamp fault diagnosis method and system

Abstract

The invention discloses an LED lighting lamp fault diagnosis method and system, and relates to the technical field of electrical fault testing. The LED lighting lamp fault diagnosis method comprises the following steps: acquiring current fault data and normal data; based on the current fault data and the normal data, obtaining current fault performance characteristics; acquiring historical fault data; based on the historical fault data, obtaining a diagnosis weight; obtaining an abnormal similarity based on the current fault data and the historical fault data; and obtaining the current fault type of the LED lighting lamp based on the abnormal similarity and the diagnosis weight. According to the invention, when fault diagnosis is carried out on the collected data subsequently, different diagnosis weights are given to different types of data under different types of faults, so that the actual fault type is accurately judged, and the accuracy of fault diagnosis of the LED lighting lamp is improved.

Description

Technical Field

[0001] The present application relates to the technical field of electrical fault testing, and in particular to a method and system for diagnosing faults of LED lighting fixtures. Background Art

[0002] With the rapid development of science and technology, light-emitting diode (LED) lighting technology has gradually become the mainstream of the lighting market due to its advantages such as high efficiency, energy saving and environmental protection. LED lighting fixtures are widely used in various fields such as home, business and industry, which has greatly promoted the transformation of the lighting industry. When diagnosing the fault of LED lighting fixtures, it is usually necessary to check the measured values ​​of various types of data of LED lighting fixtures that can be monitored one by one to determine the fault type of LED lighting fixtures.

[0003] When an LED lighting fixture fails, the measured values ​​of various types of data of the LED lighting fixture will have a certain response, but for different types of faults, similar characteristics are likely to appear under the same dimensional type of data, which will eventually lead to misjudgment of the fault detection of the LED lighting fixture. At the same time, due to the differences in the series and parallel combination methods of different LED lighting fixtures, for example, for large LED lighting fixtures, each series circuit may contain more lamp beads, so the probability of failure and actual performance are also different. Therefore, when using historical fault data to judge the fault type of the current fault data (that is, the fault data corresponding to the LED lighting fixture to be detected), even the monitoring data between different specifications of LED lighting fixtures with the same fault type are also quite different, which leads to misjudgment of the fault type of the current LED lighting fixture that has a fault. Summary of the invention

[0004] The purpose of the present application is to provide a method and system for diagnosing faults of LED lighting fixtures, so as to solve the technical problem that the prior art cannot accurately judge the fault type of the LED lighting fixture to be detected based on the current fault data.

[0005] To achieve the above objectives, this application provides the following technical solutions: In a first aspect, the present application proposes a technical solution for a method for diagnosing a fault of an LED lighting fixture, the method for diagnosing a fault of an LED lighting fixture comprising: Acquire current fault data and normal data; the current fault data at least includes current, voltage and temperature data of the LED lighting fixture during the current fault period; the normal data at least includes current, voltage and temperature data of the LED lighting fixture during normal use; Based on the current fault data and the normal data, a current fault manifestation feature is obtained; the fault manifestation feature is at least used to characterize the difference between any data of the same type in the current fault data and the normal data of the LED lighting fixture; Acquire historical fault data; the historical fault data at least includes historical fault performance characteristics and historical fault types corresponding to each historical fault of the LED lighting fixture; Based on the historical fault data, a diagnostic weight is obtained; the diagnostic weight is at least used to characterize the correlation between the historical fault type and the historical fault manifestation characteristics; Based on the current fault data and the historical fault data, obtaining anomaly similarity; Based on the abnormal similarity and the diagnosis weight, the current fault type of the LED lighting fixture is acquired.

[0006] As a specific solution in the technical solution of the present application, the obtaining of the current fault manifestation characteristics based on the current fault data and the normal data includes: Based on the current fault data, a first data value is acquired; the first data value is a data value of any type of data in the current fault data; Based on the normal data, obtaining a second data value; the second data value has the same data type as the first data value; Obtaining a feature difference value based on subtracting the second data value from the first data value; Based on the characteristic difference value, an abnormal change trend value is obtained; the abnormal change trend value is at least used to characterize the change trend of the characteristic difference value over time; Based on the abnormal change trend value, the current fault manifestation feature is obtained.

[0007] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the abnormal change trend value based on the characteristic difference is as follows: in, Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of times the r-th type of data is collected in the current fault time period; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Represents the characteristic difference of the rth type of data collected at the t+1th time during the current fault time period; It means to find the absolute value; is any constant greater than 0.

[0008] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the current fault manifestation characteristics based on the abnormal change trend value is as follows: in, Indicates the current fault performance characteristics of the rth type of data in the current fault time period; Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of the r-th type of data collected in the current fault time period, and N is a positive integer greater than or equal to 1; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Indicates the absolute value.

[0009] As a specific solution in the technical solution of the present application, the obtaining of the diagnosis weight based on the historical fault data includes: Based on the historical fault data, a first historical fault manifestation feature, a second historical fault manifestation feature, a first average value, and a second average value are obtained; the first historical fault manifestation feature and the second historical fault manifestation feature are any two different historical fault manifestation features in the historical fault data, and the first historical fault manifestation feature and the second historical fault manifestation feature correspond to the same historical fault type; the first average value is the average value of each feature difference corresponding to the first historical fault manifestation feature; the second average value is the average value of each feature difference corresponding to the second historical fault manifestation feature; Based on the first historical fault manifestation feature and the second historical fault manifestation feature, obtaining a first difference; Based on the first average value and the second average value, obtaining a second difference value; Based on the first difference and the second difference, obtaining an increase coefficient; the increase coefficient is at least used to characterize the difference between the first difference and the second difference; Based on the increase coefficient, a diagnosis weight is obtained.

[0010] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the increase coefficient based on the first difference and the second difference is as follows: in, Indicates the increase coefficient of the performance characteristics of the i-th and k-th historical faults; represents the performance characteristics of the i-th historical fault; represents the kth historical fault performance characteristics; Represents the average value of each feature difference corresponding to the i-th historical fault performance feature; Represents the average value of each feature difference corresponding to the k-th historical fault performance feature; is any constant greater than 0; Indicates the absolute value.

[0011] As a specific solution in the technical solution of this application, the calculation formula for obtaining the diagnostic weight based on the increase coefficient is as follows: in, represents the diagnostic weight of the fault manifestation feature corresponding to the r-th type of data for the first historical fault type; the first historical fault type is the same as the historical fault type corresponding to the first historical fault manifestation feature and the second historical fault manifestation feature; M represents the number of all increase coefficients of the r-th type of data corresponding to the first historical fault type, and M is a positive integer greater than or equal to 2; Indicates the xth increase coefficient; Indicates the y-th increase coefficient; is any constant greater than 0; Represents a normalization function, which is used to map the values ​​in brackets to the range of [0, 1].

[0012] As a specific solution in the technical solution of the present application, the obtaining of abnormal similarity based on the current fault data and the historical fault data includes: Based on the current fault data, obtaining a first fault manifestation feature; Based on the historical fault data, obtaining at least one second fault manifestation feature; the data type corresponding to the second fault manifestation feature is the same as the data type corresponding to the first fault manifestation feature; Based on the first fault manifestation feature and each second fault manifestation feature, anomaly similarity is acquired.

[0013] As a specific solution in the technical solution of the present application, the calculation formula for obtaining the abnormal similarity based on the first fault manifestation feature and each second fault manifestation feature is as follows: in, Indicates the abnormal similarity corresponding to the rth type of data in the current fault data; Indicates the first fault manifestation feature corresponding to the rth type of data in the current fault data; represents the number of second fault manifestation characteristics corresponding to the rth type of data in the historical fault data, where T is a positive integer greater than or equal to 1; Indicates the g-th second fault manifestation feature corresponding to the r-th type of data in the historical fault data; It means to find the absolute value; is any constant greater than 0.

[0014] In a second aspect, the present application proposes a technical solution for a LED lighting fixture fault diagnosis system, the LED lighting fixture fault diagnosis system comprising: A reader, used to obtain current fault data and normal data; the current fault data at least includes current, voltage and temperature data of the LED lighting fixture during the current fault period; the normal data at least includes current, voltage and temperature data of the LED lighting fixture during normal use; A processor, configured to obtain a current fault manifestation feature based on the current fault data and the normal data; the fault manifestation feature is at least used to characterize a difference between any data of the same type in the current fault data and the normal data of the LED lighting fixture; The reader is also used to obtain historical fault data; the historical fault data at least includes historical fault performance characteristics and historical fault types corresponding to each historical fault of the LED lighting fixture; The processor is further used to obtain a diagnosis weight based on the historical fault data; the diagnosis weight is at least used to characterize the correlation between the historical fault type and the historical fault manifestation characteristics; and, based on the current fault data and the historical fault data, obtaining anomaly similarity; And, based on the abnormal similarity and the diagnosis weight, the current fault type of the LED lighting fixture is obtained.

[0015] As a specific solution in the technical solution of the present application, the processor is further used to obtain a first data value based on the current fault data; the first data value is a data value of any type of data in the current fault data; And, based on the normal data, obtaining a second data value; the second data value has the same data type as the first data value; and obtaining a characteristic difference value based on subtracting the second data value from the first data value; And, based on the characteristic difference value, an abnormal change trend value is obtained; the abnormal change trend value is at least used to characterize the change trend of the characteristic difference value over time; And, based on the abnormal change trend value, the current fault manifestation characteristics are obtained.

[0016] As a specific solution in the technical solution of the present application, the processor obtains the calculation formula of the abnormal change trend value based on the characteristic difference as follows: in, Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of times the r-th type of data is collected in the current fault time period; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Represents the characteristic difference of the rth type of data collected at the t+1th time during the current fault time period; It means to find the absolute value; is any constant greater than 0.

[0017] As a specific solution in the technical solution of the present application, the processor obtains the calculation formula of the current fault manifestation characteristics based on the abnormal change trend value as follows: in, Indicates the current fault performance characteristics of the rth type of data in the current fault time period; Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of the r-th type of data collected in the current fault time period, and N is a positive integer greater than or equal to 1; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Indicates the absolute value.

[0018] As a specific solution in the technical solution of the present application, the processor is further used to obtain a first historical fault manifestation feature, a second historical fault manifestation feature, a first average value, and a second average value based on the historical fault data; the first historical fault manifestation feature and the second historical fault manifestation feature are any two different historical fault manifestation features in the historical fault data, and the first historical fault manifestation feature and the second historical fault manifestation feature correspond to the same historical fault type; the first average value is the average value of each feature difference corresponding to the first historical fault manifestation feature; the second average value is the average value of each feature difference corresponding to the second historical fault manifestation feature; And, based on the first historical fault manifestation feature and the second historical fault manifestation feature, obtaining a first difference; And, based on the first average value and the second average value, obtaining a second difference value; And, based on the first difference and the second difference, an increase coefficient is obtained; the increase coefficient is at least used to characterize the difference between the first difference and the second difference; And, based on the increase coefficient, a diagnosis weight is obtained.

[0019] As a specific solution in the technical solution of the present application, the processor obtains the calculation formula of the increase coefficient based on the first difference and the second difference as follows: in, Indicates the increase coefficient of the performance characteristics of the i-th and k-th historical faults; represents the performance characteristics of the i-th historical fault; represents the kth historical fault performance characteristics; Represents the average value of each feature difference corresponding to the i-th historical fault performance feature; Represents the average value of each feature difference corresponding to the k-th historical fault performance feature; is any constant greater than 0; Indicates the absolute value.

[0020] As a specific solution in the technical solution of the present application, the processor obtains the calculation formula of the diagnosis weight based on the increase coefficient as follows: in, represents the diagnostic weight of the fault manifestation feature corresponding to the r-th type of data for the first historical fault type; the first historical fault type is the same as the historical fault type corresponding to the first historical fault manifestation feature and the second historical fault manifestation feature; M represents the number of all increase coefficients of the r-th type of data corresponding to the first historical fault type, and M is a positive integer greater than or equal to 2; Indicates the xth increase coefficient; Indicates the y-th increase coefficient; is any constant greater than 0; Represents a normalization function, which is used to map the values ​​in brackets to the range of [0, 1].

[0021] As a specific solution in the technical solution of the present application, the processor is further used to obtain a first fault manifestation feature based on the current fault data; And, based on the historical fault data, obtaining at least one second fault manifestation feature; the data type corresponding to the second fault manifestation feature is the same as the data type corresponding to the first fault manifestation feature; And, based on the first fault manifestation feature and each second fault manifestation feature, an abnormality similarity is obtained.

[0022] As a specific solution in the technical solution of the present application, the processor obtains the calculation formula of abnormal similarity based on the first fault manifestation feature and each second fault manifestation feature as follows: in, Indicates the abnormal similarity corresponding to the rth type of data in the current fault data; Indicates the first fault manifestation feature corresponding to the rth type of data in the current fault data; represents the number of second fault manifestation characteristics corresponding to the rth type of data in the historical fault data, where T is a positive integer greater than or equal to 1; Indicates the g-th second fault manifestation feature corresponding to the r-th type of data in the historical fault data; It means to find the absolute value; is any constant greater than 0.

[0023] Compared with the prior art, the beneficial effects of this application are: The embodiment of the LED lighting fixture fault diagnosis system proposed in the present application analyzes the commonalities in the characteristics of the same monitoring type data under lamps of different specifications that produce the same fault type, and based on the commonalities, analyzes the similarity of the changing trends in the historical fault data of the current type of fault, thereby obtaining the diagnostic weight of the data of this type of monitoring type for the current type of fault. When subsequently diagnosing faults on the collected data, different diagnostic weights are assigned to different types of data under different types of faults, thereby accurately judging the actual fault type. This operation avoids the large differences between the monitoring data of lamps of different specifications with the same fault, which in turn avoids the phenomenon of misjudgment of the fault type of the LED lighting fixture that is currently faulty, thereby improving the accuracy of LED lighting fixture fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of a flow chart of a method for diagnosing faults of LED lighting fixtures proposed in an embodiment of the present application; Figure 2 This is a schematic diagram of the structure of an LED lighting fixture fault diagnosis system proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] The terms "first", "second", etc. in the specification of the embodiment of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence, such as the first average value and the second average value proposed below, which belong to different average values. It should be understood that the average values ​​used in this way can be interchanged in appropriate cases, so that the embodiments described here can be implemented in an order other than the content illustrated or described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment including a series of steps or modules need not be limited to those steps or modules clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products or equipment, and the division of the modules appearing in the embodiment of the present application is only a logical division. There may be other division modes when implemented in practical applications, such as multiple modules can be combined into or integrated in another system, or some features can be ignored, or not executed, in addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, and the indirect coupling or communication connection between modules can be electrical or other similar forms, which are not limited in the embodiment of the present application. Furthermore, the modules or sub-modules described as separate components may or may not be physically separated, may or may not be physical modules, or may be distributed in multiple circuit modules, and some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiment of the present application.

[0027] Before understanding the embodiments of the present application, it should be clear that a light emitting diode is a semiconductor light source, and its lighting principle is based on the electroluminescent effect of semiconductor materials. The core component of the lamp is an LED chip, which is mainly composed of a PN junction, an electrode, a packaging material, and a lens or a reflector. The PN junction is composed of a P-type semiconductor and an N-type semiconductor, and is the source of LED light emission. The electrode is used to connect an external circuit and provide current, and the lens or reflector is used to control the direction and distribution of light. When the external circuit applies a forward voltage, electrons move from the N region to the P region, and holes move from the P region to the N region. Electrons and holes meet near the PN junction to form a composite. During the composite process, electrons transition from a high energy level to a low energy level, releasing energy. The released energy is emitted in the form of photons, thereby generating light of a certain intensity. As an efficient and environmentally friendly lighting device, LED lighting fixtures have the advantages of long life and high energy efficiency, but various faults may still occur during use.

[0028] LED lighting fixtures are usually composed of several lamp beads. According to prior knowledge, LED lighting fixtures are usually connected in series and parallel. They are usually divided into multiple small sections. The lamp beads in each section are connected in series, and the sections are connected in parallel. For example, every 3 lamp beads are connected in series as a group, and then multiple groups are connected in parallel. The advantage of this connection method is that when a local section fails, it will not affect the normal operation of the lamp beads in other sections.

[0029] In order to solve the technical problem mentioned in the background technology that the prior art cannot accurately judge the fault type of the LED lighting fixture to be detected based on the current fault data, this application proposes an embodiment of a LED lighting fixture fault diagnosis method. Specifically, Figure 1 As shown, the LED lighting fixture fault diagnosis method includes steps S100 to S600.

[0030] Step S100: Acquire current fault data and normal data.

[0031] As can be seen from the background technology, in this embodiment, the current fault data refers to the relevant data in the time period after the LED lighting fixture fails when in use; the normal data refers to the relevant data in the time period before the LED lighting fixture fails. In this embodiment, the current fault data at least includes the current, voltage and temperature data in the current fault time period of the LED lighting fixture. The normal data at least includes the current, voltage and temperature data when the LED lighting fixture is in normal use.

[0032] It should be noted that when an LED lighting fixture fails, various types of data will have certain responses, but for different types of failures, similar features are likely to appear under the same dimensional type of data, which may lead to misjudgment of the fault detection of LED lighting fixtures. For example: if some of the lamp beads in the LED lighting fixture are not lit, it may be due to the protection mechanism triggered by a short circuit, causing the lamp beads in a certain section or multiple sections to not light up, or it may be due to damage to the chip of the lamp bead itself, and the above two have differences and approximate relationships in the performance of multiple dimensional data such as current, voltage, and temperature. According to the analysis, for several lamp beads in series, when any lamp bead fails, it usually affects the operation of other surrounding lamp beads in series. At the same time, for multiple groups of lamp beads in different series states, the data size and trend of various types of data between different series groups under different failures are also different.

[0033] Step S200: Based on the current fault data and the normal data, obtain the current fault manifestation characteristics.

[0034] It should be noted that for any specification of LED lighting fixtures, the rated normal working state data will be set during the working process, such as the current, voltage or temperature value during normal working. If the LED lighting fixture is abnormal, there must be a difference between the fault data and the normal data in the time period after the fault occurs. Therefore, the current fault performance characteristics can be obtained based on the current fault data and the normal data. It is easy to understand that in a period of time before the occurrence of different types of faults, the data of various types of lamp beads have a certain upward or downward trend. For example, when the lamp beads flash, the current may fluctuate to a certain extent, and the temperature may increase to a certain extent. At the same time, combined with the above, it can be seen that when any lamp bead fails, it usually affects the operation of other surrounding lamp beads connected in series. In other words, in the embodiment of the present application, the change of these data (that is, the current fault performance characteristics) can be used to determine what type of fault the LED lighting fixture has. Therefore, in this embodiment, the fault performance characteristics are at least used to characterize the difference between the current fault data and any data of the same type in the normal data of the LED lighting fixture. As can be seen from the foregoing, the types of data include current, voltage and temperature, etc., which will not be described one by one in the following.

[0035] In order to obtain the current fault manifestation characteristics that accurately characterize the difference between the current fault data of the LED lighting fixture and any data of the same type in the normal data, in an embodiment of the present application, step S200, based on the current fault data and the normal data, obtains the current fault manifestation characteristics, which may include steps S210 to S250.

[0036] Step S210: Based on the current fault data, a first data value is obtained.

[0037] In this embodiment, the first data value is a data value of any type of data in the current fault data. For example, the first data value may be a current value, a voltage value, or a temperature value in the current fault data.

[0038] Step S220: Based on the normal data, obtain a second data value.

[0039] In this embodiment, the second data value has the same data type as the first data value. In this embodiment, the rated value can be taken as the second data value, and of course, the average value of all data values ​​of the same data type of normal data can also be taken as the second data value.

[0040] Step S230: Obtain a feature difference value based on subtracting the second data value from the first data value.

[0041] In this embodiment, any reasonable method can be used to obtain the characteristic difference value based on the first data value minus the second data value. For example, in one embodiment of the present application, step S230, based on the first data value minus the second data value, obtains the characteristic difference value by the following calculation formula: in, Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; represents the first data value corresponding to the r-th type of data collected for the t-th time during the current fault time period; Represents the second data value corresponding to the rth type of data.

[0042] Step S240: Based on the characteristic difference, obtain the abnormal change trend value.

[0043] In this embodiment, the abnormal change trend value is at least used to characterize the change trend of the characteristic difference value over time. It should be clear that in a certain type of fault, the greater the trend of the characteristic difference value changing over time, the stronger the correlation between the characteristic difference value and the type of fault, so the correlation between various characteristic difference values ​​and various fault types can be determined later through the abnormal change trend value.

[0044] In the embodiment of the present application, any reasonable method can be used to obtain the abnormal change trend value based on the characteristic difference value. For example, in step S240, the calculation formula for obtaining the abnormal change trend value based on the characteristic difference value can be as follows: in, Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of times the r-th type of data is collected in the current fault time period; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Represents the characteristic difference of the rth type of data collected at the t+1th time during the current fault time period; It means to find the absolute value; is any constant greater than 0.

[0045] In this embodiment, the abnormal change trend value The abnormal change trend value is obtained by respectively obtaining the difference between the abnormal levels of two adjacent sampling points and accumulating the absolute value of the difference and then combining them in the form of a fraction. The value range of is within the interval of [-1,1]. When the value is closer to -1, it means that the abnormal level has a tendency to decrease and deviate from the normal value (that is, the second data value in the previous article). Conversely, when the value is closer to 1, it means that the abnormal level has a tendency to increase and deviate from the normal value. When it is closer to 0, it means that the abnormal level is relatively stable.

[0046] Step S250: Based on the abnormal change trend value, the current fault manifestation characteristics are obtained.

[0047] In an embodiment of the present application, the abnormal change trend value can be directly used as the current fault manifestation feature. In order to amplify the current fault manifestation feature so that the current fault manifestation feature is more obvious, in an embodiment of the present application, step S250, based on the abnormal change trend value, obtains the calculation formula of the current fault manifestation feature as follows: in, Indicates the current fault performance characteristics of the rth type of data in the current fault time period; Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of the r-th type of data collected in the current fault time period, and N is a positive integer greater than or equal to 1; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Indicates the absolute value.

[0048] In this embodiment, the current fault has the following characteristics: The abnormal change trend value and the cumulative value of the absolute value of the characteristic difference are combined to obtain the current fault performance characteristics. It shows one of the characteristics of local circuit fault in the monitoring period before the fault occurs in the rth type of data.

[0049] Step S300: Acquire historical fault data.

[0050] In this embodiment, the historical fault data at least includes historical fault manifestation characteristics and historical fault types corresponding to each historical fault of the LED lighting fixture. The LED lighting fixture in the historical fault data may be the same type as the LED lighting fixture that needs to be diagnosed for fault, or may be different from the type of the LED lighting fixture that needs to be diagnosed for fault.

[0051] It should be noted that due to the differences in the series and parallel combinations of different LED lighting fixtures, for example, for large LED lighting fixtures, each series circuit may contain more lamp beads, so the probability of failure and actual performance are also different. Therefore, when using historical fault data to judge the current fault type of LED lighting fixtures, there are also large differences in the monitoring data between different specifications of lamps with the same fault, which can easily lead to misjudgment of the fault type of the current faulty LED lighting fixture based on historical fault data.

[0052] It should be noted that for any type of fault, there must be one or several obvious changes in the data characteristics of the monitoring type. For example, when flickering is caused by poor power contact, the temperature of the lamp beads in all series circuits will increase compared to other types of faults. For other faults also caused by poor power contact, the temperature will increase. However, for other dimensional data, such as current or voltage, the fluctuation amplitudes are different. Therefore, for the fault of poor power contact, the temperature data type has a greater weight in its diagnosis.

[0053] Step S400: Obtaining a diagnosis weight based on the historical fault data.

[0054] In this embodiment, the diagnostic weight is at least used to characterize the correlation between the historical fault type and the historical fault performance characteristics. As can be seen from the foregoing, when the same type of fault occurs, for the same monitoring type data, there is a difference in the range of change between the historical fault performance characteristics of different historical faults, that is, the monitoring data generated by the series circuit containing more lamp beads is approximately linear compared to the series circuit containing fewer lamp beads, and the actual growth rate is determined by the rated data of different dimensional types. Based on this, the weight occupied by the historical fault performance characteristics corresponding to each fault type when it occurs can be determined by the historical fault performance characteristics and the corresponding historical fault types (that is, the diagnostic weight below). In an embodiment of the present application, any reasonable method can be used to obtain the diagnostic weight based on the historical fault data. For example, in one embodiment of the present application, step S400, based on the historical fault data, obtains the diagnostic weight, including steps S410 to S450.

[0055] Step S410: Based on the historical fault data, a first historical fault manifestation feature, a second historical fault manifestation feature, a first average value, and a second average value are obtained.

[0056] In this embodiment, the first historical fault manifestation feature and the second historical fault manifestation feature are any two different historical fault manifestation features in the historical fault data, and the first historical fault manifestation feature and the second historical fault manifestation feature correspond to the same historical fault type; the first average value is the average value of each feature difference corresponding to the first historical fault manifestation feature; the second average value is the average value of each feature difference corresponding to the second historical fault manifestation feature.

[0057] Step S420: obtaining a first difference based on the first historical fault manifestation feature and the second historical fault manifestation feature.

[0058] It should be clear that obtaining the corresponding difference based on two values ​​is a mature technology and will not be described in detail here.

[0059] Step S430: obtaining a second difference based on the first average value and the second average value.

[0060] It should be clear that obtaining the corresponding difference based on two values ​​is a mature technology and will not be described in detail here.

[0061] Step S440: Obtain an increase coefficient based on the first difference and the second difference.

[0062] In this embodiment, the increase coefficient is at least used to characterize the difference between the first difference and the second difference. It is easy to understand that if the first difference and the second difference are similar in size, it means that the first historical fault manifestation characteristics and the second historical fault manifestation characteristics have a greater impact on the historical fault type. In an embodiment of the present application, the increase coefficient can be obtained in any reasonable manner based on the first difference and the second difference. For example, in a specific embodiment, step S440, based on the first difference and the second difference, the calculation formula for obtaining the increase coefficient is as follows: in, Indicates the increase coefficient of the performance characteristics of the i-th and k-th historical faults; represents the performance characteristics of the i-th historical fault; represents the kth historical fault performance characteristics; Represents the average value of each feature difference corresponding to the i-th historical fault performance feature; Represents the average value of each feature difference corresponding to the k-th historical fault performance feature; is any constant greater than 0; In this embodiment, the increase coefficients of the i-th and k-th historical fault data are obtained. The larger the value, the more obvious the characteristics of the current r-th type of data in the i-th and k-th historical fault data are. In other words, it is more necessary to adjust the weight of the r-th type of data in similar faults in the future.

[0063] Step S450: Obtain a diagnosis weight based on the increase coefficient.

[0064] In an embodiment of the present application, any reasonable method can be used to obtain the diagnostic weight based on the increase coefficient. For example, the increase coefficient is directly used as the diagnostic weight. In a specific embodiment of the present application, step S450, based on the increase coefficient, the calculation formula for obtaining the diagnostic weight is as follows: in, represents the diagnostic weight of the fault manifestation feature corresponding to the r-th type of data for the first historical fault type; the first historical fault type is the same as the historical fault type corresponding to the first historical fault manifestation feature and the second historical fault manifestation feature; M represents the number of all increase coefficients of the r-th type of data corresponding to the first historical fault type, and M is a positive integer greater than or equal to 2; Indicates the xth increase coefficient; Indicates the y-th increase coefficient; is any constant greater than 0; Represents a normalization function, which is used to map the values ​​in brackets to the range of [0, 1].

[0065] In this embodiment, and Represents the combination of any two different increase coefficients. Obtain the difference between the increase coefficients of all r-th type data of the same fault type (that is, ), the smaller the value, the more it means that when the current r-th type of data corresponds to this type of fault, there must be a rule that is affected by different lamp specifications. At the same time, the mean value of the increase coefficient of all combinations is obtained (that is, ), the larger the value, the more obvious the performance of the current r-th type of data is for this type of fault compared with other types of data. Therefore, the diagnostic weight It can show the weight of the rth monitoring data for the judgment of this type of fault.

[0066] Step S500: Acquire abnormality similarity based on the current fault data and the historical fault data.

[0067] It should be clear that if the similarity between the current fault data and the historical fault data is higher, it means that the fault type of the LED lighting fixture in the current fault data is more similar to the fault type of the LED lighting fixture in the historical fault data. In an embodiment of the present application, any reasonable method can be used to obtain abnormal similarity based on the current fault data and the historical fault data. For example, the abnormal similarity can be obtained using a cosine similarity algorithm or a Pearson correlation coefficient. In a specific embodiment of the present application, step S500, based on the current fault data and the historical fault data, obtains abnormal similarity, including steps S510 to S530.

[0068] Step S510: Based on the current fault data, a first fault manifestation feature is obtained.

[0069] It should be clear that based on the fault data (ie, the current fault data), the corresponding fault manifestation feature (ie, the first fault manifestation feature) can be obtained, and reference may be made to step S100 to step S200, which will not be elaborated here.

[0070] Step S520: Based on the historical fault data, obtain at least one second fault manifestation feature.

[0071] In this embodiment, the data type corresponding to the second fault manifestation feature is the same as the data type corresponding to the first fault manifestation feature. Based on the fault data (ie, historical fault data), the corresponding fault manifestation feature (ie, the second fault manifestation feature) is obtained, which can refer to steps S100 to S200 and will not be described in detail here.

[0072] Step S530: Acquire abnormality similarity based on the first fault manifestation feature and each second fault manifestation feature.

[0073] In this embodiment, the cosine similarity algorithm or the Pearson correlation coefficient can be used to obtain the abnormal similarity based on the first fault manifestation feature and each second fault manifestation feature. In a specific embodiment of the present application, step S530, based on the first fault manifestation feature and each second fault manifestation feature, the calculation formula for obtaining the abnormal similarity is as follows: in, Indicates the abnormal similarity corresponding to the rth type of data in the current fault data; Indicates the first fault manifestation feature corresponding to the rth type of data in the current fault data; represents the number of second fault manifestation characteristics corresponding to the rth type of data in the historical fault data, where T is a positive integer greater than or equal to 1; Indicates the g-th second fault manifestation feature corresponding to the r-th type of data in the historical fault data; It means to find the absolute value; is any constant greater than 0.

[0074] Step S600: Based on the abnormal similarity and the diagnosis weight, the current fault type of the LED lighting fixture is obtained.

[0075] In this embodiment, based on the abnormal similarity and the diagnostic weight, the calculation formula for obtaining the current fault type of the LED lighting fixture is as follows: in, represents the probability of the current fault type; G represents the total number of data of different types; Indicates the abnormal similarity corresponding to the rth type of data in the current fault data; represents the diagnostic weight of the fault manifestation characteristics corresponding to the rth type of data for the first historical fault type; the probability of the current fault type The larger the value, the more similar the current fault of the LED lighting fixture is to a certain historical fault data of a certain fault, and the more likely the current fault type is of that type. The fault type corresponding to the historical fault data with the highest probability can be used as the current fault type, and the diagnosed data can be transmitted to the user or staff's mobile or fixed equipment through the Internet of Things for subsequent maintenance reference.

[0076] The embodiment of the LED lighting fixture fault diagnosis method proposed in the present application analyzes the commonalities in the characteristics of the same monitoring type data under lamps of different specifications that produce the same fault type, and based on the commonalities, analyzes the similarity of the changing trends in the historical fault data of the current type of fault, thereby obtaining the diagnostic weight of the data of this type of monitoring type for the current type of fault. When subsequently diagnosing faults on the collected data, different diagnostic weights are assigned to different types of data under different types of faults, thereby accurately judging the actual fault type. This operation avoids the large differences between the monitoring data of lamps of different specifications with the same fault, which in turn avoids the phenomenon of misjudgment of the fault type of the LED lighting fixture that is currently faulty, thereby improving the accuracy of LED lighting fixture fault diagnosis.

[0077] After introducing the LED lighting fixture fault diagnosis method proposed in the embodiment of the present application, the following introduces an LED lighting fixture fault diagnosis system proposed in the present application. Figure 2 As shown, the LED lighting fixture fault diagnosis system 10 includes: The reader 11 is used to obtain current fault data and normal data; the current fault data at least includes the current, voltage and temperature data of the LED lighting fixture during the current fault period; the normal data at least includes the current, voltage and temperature data of the LED lighting fixture during normal use; The processor 12 is used to obtain a current fault manifestation feature based on the current fault data and the normal data; the fault manifestation feature is at least used to characterize the difference between any data of the same type in the current fault data and the normal data of the LED lighting fixture; The reader 11 is also used to obtain historical fault data; the historical fault data at least includes historical fault performance characteristics and historical fault types corresponding to each historical fault of the LED lighting fixture; The processor 12 is further used to obtain a diagnosis weight based on the historical fault data; the diagnosis weight is at least used to characterize the correlation between the historical fault type and the historical fault manifestation characteristics; and, based on the current fault data and the historical fault data, obtaining anomaly similarity; And, based on the abnormal similarity and the diagnosis weight, the current fault type of the LED lighting fixture is obtained.

[0078] As a specific embodiment of the present application, the processor 12 is further configured to obtain a first data value based on the current fault data; the first data value is a data value of any type of data in the current fault data; And, based on the normal data, obtaining a second data value; the second data value has the same data type as the first data value; and obtaining a characteristic difference value based on subtracting the second data value from the first data value; And, based on the characteristic difference value, an abnormal change trend value is obtained; the abnormal change trend value is at least used to characterize the change trend of the characteristic difference value over time; And, based on the abnormal change trend value, the current fault manifestation characteristics are obtained.

[0079] As a specific embodiment of the present application, the processor 12 obtains the calculation formula of the abnormal change trend value based on the characteristic difference value as follows: in, Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of times the r-th type of data is collected in the current fault time period; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Represents the characteristic difference of the rth type of data collected at the t+1th time during the current fault time period; It means to find the absolute value; is any constant greater than 0.

[0080] As a specific embodiment of the present application, the processor 12 obtains the calculation formula of the current fault manifestation feature based on the abnormal change trend value as follows: in, Indicates the current fault performance characteristics of the rth type of data in the current fault time period; Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of the r-th type of data collected in the current fault time period, and N is a positive integer greater than or equal to 1; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Indicates the absolute value.

[0081] As a specific embodiment of the present application, the processor 12 is further used to obtain a first historical fault manifestation feature, a second historical fault manifestation feature, a first average value, and a second average value based on the historical fault data; the first historical fault manifestation feature and the second historical fault manifestation feature are any two different historical fault manifestation features in the historical fault data, and the first historical fault manifestation feature and the second historical fault manifestation feature correspond to the same historical fault type; the first average value is the average value of each feature difference corresponding to the first historical fault manifestation feature; the second average value is the average value of each feature difference corresponding to the second historical fault manifestation feature; And, based on the first historical fault manifestation feature and the second historical fault manifestation feature, obtaining a first difference; And, based on the first average value and the second average value, obtaining a second difference value; And, based on the first difference and the second difference, an increase coefficient is obtained; the increase coefficient is at least used to characterize the difference between the first difference and the second difference; And, based on the increase coefficient, a diagnosis weight is obtained.

[0082] As a specific embodiment of the present application, the processor 12 obtains the calculation formula of the increase coefficient based on the first difference and the second difference as follows: in, Indicates the increase coefficient of the performance characteristics of the i-th and k-th historical faults; represents the performance characteristics of the i-th historical fault; represents the kth historical fault performance characteristics; Represents the average value of each feature difference corresponding to the i-th historical fault performance feature; Represents the average value of each feature difference corresponding to the k-th historical fault performance feature; is any constant greater than 0; Indicates the absolute value.

[0083] As a specific embodiment of the present application, the processor 12 obtains the calculation formula of the diagnosis weight based on the increase coefficient as follows: in, represents the diagnostic weight of the fault manifestation feature corresponding to the r-th type of data for the first historical fault type; the first historical fault type is the same as the historical fault type corresponding to the first historical fault manifestation feature and the second historical fault manifestation feature; M represents the number of all increase coefficients of the r-th type of data corresponding to the first historical fault type, and M is a positive integer greater than or equal to 2; Indicates the xth increase coefficient; Indicates the y-th increase coefficient; is any constant greater than 0; Represents a normalization function, which is used to map the values ​​in brackets to the range of [0, 1].

[0084] As a specific embodiment of the present application, the processor 12 is further configured to obtain a first fault manifestation feature based on the current fault data; And, based on the historical fault data, obtaining at least one second fault manifestation feature; the data type corresponding to the second fault manifestation feature is the same as the data type corresponding to the first fault manifestation feature; And, based on the first fault manifestation feature and each second fault manifestation feature, an abnormality similarity is obtained.

[0085] As a specific embodiment of the present application, the processor 12 obtains the calculation formula of abnormal similarity based on the first fault manifestation feature and each second fault manifestation feature as follows: in, Indicates the abnormal similarity corresponding to the rth type of data in the current fault data; Indicates the first fault manifestation feature corresponding to the rth type of data in the current fault data; represents the number of second fault manifestation characteristics corresponding to the rth type of data in the historical fault data, where T is a positive integer greater than or equal to 1; Indicates the g-th second fault manifestation feature corresponding to the r-th type of data in the historical fault data; It means to find the absolute value; is any constant greater than 0.

[0086] The embodiment of the LED lighting fixture fault diagnosis system proposed in the present application analyzes the commonalities in the characteristics of the same monitoring type data under lamps of different specifications that produce the same fault type, and based on the commonalities, analyzes the similarity of the changing trends in the historical fault data of the current type of fault, thereby obtaining the diagnostic weight of the data of this type of monitoring type for the current type of fault. When subsequently diagnosing faults on the collected data, different diagnostic weights are assigned to different types of data under different types of faults, thereby accurately judging the actual fault type. This operation avoids the large differences between the monitoring data of lamps of different specifications with the same fault, which in turn avoids the phenomenon of misjudgment of the fault type of the LED lighting fixture that is currently faulty, thereby improving the accuracy of LED lighting fixture fault diagnosis.

[0087] It should be clear that the computer-readable storage media in this application include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory, static random access memory, dynamic random access memory, other types of random access memory, read-only memory, electrically erasable programmable read-only memory, flash memory or other memory technology, read-only compact disc read-only memory, digital versatile disc or other optical storage, magnetic cassettes, 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, such as modulated data signals and carrier waves.

[0088] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0089] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the methods, devices and equipment described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0090] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0091] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0092] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0093] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0094] The computer program product includes one or more computer instructions. When the computer program is loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disk), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0095] Although the embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles of the present application.

Claims

1. A method for diagnosing faults of LED lighting fixtures, characterized in that: include: Get current fault data and normal data; The current fault data at least includes current, voltage and temperature data of the LED lighting fixture within the current fault time period; The normal data at least includes current, voltage and temperature data when the LED lighting fixture is in normal use; Based on the current fault data and the normal data, obtaining current fault manifestation characteristics; The fault manifestation feature is at least used to characterize the difference between the current fault data of the LED lighting fixture and any data of the same type in the normal data; Acquire historical fault data; the historical fault data at least includes historical fault performance characteristics and historical fault types corresponding to each historical fault of the LED lighting fixture; Based on the historical fault data, a diagnostic weight is obtained; the diagnostic weight is at least used to characterize the correlation between the historical fault type and the historical fault manifestation characteristics; Based on the current fault data and the historical fault data, obtaining anomaly similarity; Based on the abnormal similarity and the diagnosis weight, obtaining the current fault type of the LED lighting fixture; The obtaining, based on the current fault data and the normal data, current fault manifestation characteristics includes: Based on the current fault data, a first data value is acquired; the first data value is a data value of any type of data in the current fault data; Based on the normal data, obtaining a second data value; the second data value has the same data type as the first data value; Obtaining a feature difference value based on subtracting the second data value from the first data value; Based on the characteristic difference value, an abnormal change trend value is obtained; the abnormal change trend value is at least used to characterize the change trend of the characteristic difference value over time; Based on the abnormal change trend value, obtaining the current fault manifestation characteristics; The calculation formula for obtaining the abnormal change trend value based on the characteristic difference is as follows: in, Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of times the r-th type of data is collected in the current fault time period; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Represents the characteristic difference of the rth type of data collected at the t+1th time during the current fault time period; It means to find the absolute value; is any constant greater than 0; The calculation formula for obtaining the current fault manifestation characteristics based on the abnormal change trend value is as follows: in, Indicates the current fault performance characteristics of the rth type of data in the current fault time period; Represents the abnormal change trend value of the r-th type of data in the current fault time period; N represents the total number of the r-th type of data collected in the current fault time period, and N is a positive integer greater than or equal to 1; Represents the characteristic difference of the rth type of data collected for the tth time during the current fault time period; Indicates the absolute value.

2. The LED lighting fixture fault diagnosis method according to claim 1, characterized in that: The obtaining of the diagnosis weight based on the historical fault data includes: Based on the historical fault data, a first historical fault manifestation feature, a second historical fault manifestation feature, a first average value, and a second average value are obtained; the first historical fault manifestation feature and the second historical fault manifestation feature are any two different historical fault manifestation features in the historical fault data, and the first historical fault manifestation feature and the second historical fault manifestation feature correspond to the same historical fault type; the first average value is the average value of each feature difference corresponding to the first historical fault manifestation feature; the second average value is the average value of each feature difference corresponding to the second historical fault manifestation feature; Based on the first historical fault manifestation feature and the second historical fault manifestation feature, obtaining a first difference; Based on the first average value and the second average value, obtaining a second difference value; Based on the first difference and the second difference, obtaining an increase coefficient; the increase coefficient is at least used to characterize the difference between the first difference and the second difference; Based on the increase coefficient, a diagnosis weight is obtained.

3. The LED lighting fixture fault diagnosis method according to claim 2, characterized in that: The calculation formula for obtaining the increase coefficient based on the first difference and the second difference is as follows: in, Indicates the increase coefficient of the performance characteristics of the i-th and k-th historical faults; represents the performance characteristics of the i-th historical fault; represents the kth historical fault performance characteristics; Represents the average value of each feature difference corresponding to the i-th historical fault performance feature; Represents the average value of each feature difference corresponding to the k-th historical fault performance feature; is any constant greater than 0; Indicates the absolute value.

4. The LED lighting fixture fault diagnosis method according to claim 2, characterized in that: The calculation formula for obtaining the diagnosis weight based on the increase coefficient is as follows: in, represents the diagnostic weight of the fault manifestation feature corresponding to the r-th type of data for the first historical fault type; the first historical fault type is the same as the historical fault type corresponding to the first historical fault manifestation feature and the second historical fault manifestation feature; M represents the number of all increase coefficients of the r-th type of data corresponding to the first historical fault type, and M is a positive integer greater than or equal to 2; Indicates the xth increase coefficient; Indicates the y-th increase coefficient; is any constant greater than 0; Represents a normalization function, which is used to map the values ​​in brackets to the range of [0, 1].

5. The LED lighting fixture fault diagnosis method according to any one of claims 1 to 4, characterized in that: The obtaining of abnormal similarity based on the current fault data and the historical fault data includes: Based on the current fault data, obtaining a first fault manifestation feature; Based on the historical fault data, obtaining at least one second fault manifestation feature; the data type corresponding to the second fault manifestation feature is the same as the data type corresponding to the first fault manifestation feature; Based on the first fault manifestation feature and each second fault manifestation feature, anomaly similarity is acquired.

6. The LED lighting fixture fault diagnosis method according to claim 5, characterized in that: The calculation formula for obtaining the abnormal similarity based on the first fault manifestation feature and each second fault manifestation feature is as follows: in, Indicates the abnormal similarity corresponding to the rth type of data in the current fault data; Indicates the first fault manifestation feature corresponding to the rth type of data in the current fault data; represents the number of second fault manifestation characteristics corresponding to the rth type of data in the historical fault data, where T is a positive integer greater than or equal to 1; Indicates the g-th second fault manifestation feature corresponding to the r-th type of data in the historical fault data; It means to find the absolute value; is any constant greater than 0.

7. A LED lighting fixture fault diagnosis system, characterized in that: The system is used to implement the method according to any one of claims 1 to 6, comprising: A reader, used to obtain current fault data and normal data; the current fault data at least includes current, voltage and temperature data of the LED lighting fixture during the current fault period; the normal data at least includes current, voltage and temperature data of the LED lighting fixture during normal use; A processor, configured to obtain a current fault manifestation feature based on the current fault data and the normal data; the fault manifestation feature is at least used to characterize a difference between any data of the same type in the current fault data and the normal data of the LED lighting fixture; The reader is also used to obtain historical fault data; the historical fault data at least includes historical fault performance characteristics and historical fault types corresponding to each historical fault of the LED lighting fixture; The processor is further used to obtain a diagnosis weight based on the historical fault data; the diagnosis weight is at least used to characterize the correlation between the historical fault type and the historical fault manifestation characteristics; and, based on the current fault data and the historical fault data, obtaining anomaly similarity; And, based on the abnormal similarity and the diagnosis weight, the current fault type of the LED lighting fixture is obtained.

Images