Power semiconductor fault early warning method and system based on data driving

Abstract

The invention relates to the technical field of power electronic equipment monitoring, in particular to a power semiconductor fault early-warning method and system based on data driving, and the method comprises the steps: receiving a fault early-warning instruction of a power semiconductor, determining a fault early-warning system based on the fault early-warning instruction, obtaining an electrical evaluation node based on the power semiconductor, and determining the fault early-warning system based on the electrical evaluation node. Based on a preset electrical monitoring time period, a preset electrical monitoring time interval and an electrical parameter node set obtained by the electrical parameter monitoring unit, a frequency evaluation proportion is obtained by using a low-frequency monitoring module and a high-frequency monitoring module; a primary monitoring state of the power semiconductor is confirmed based on an electrical parameter node set, a frequency evaluation proportion and an electrical evaluation node, a monitoring temperature set and a temperature change rate set are acquired by using a temperature monitoring module set, and a secondary monitoring state of the power semiconductor is confirmed based on a comprehensive monitoring temperature value and the temperature change rate set. And fault early warning of the power semiconductor is realized. According to the invention, the accuracy and reliability of power semiconductor fault early warning can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power electronic device monitoring, and particularly relates to a power semiconductor fault early warning method and system based on data driving. BACKGROUND

[0002] Power semiconductors play a core role in modern power electronic systems and are widely used in multiple fields. With the increasing complexity of power electronic devices, the failure of power semiconductors can cause system downtime or even damage, resulting in huge economic losses. Therefore, timely and accurate fault early warning of power semiconductors is of great significance to ensure the safe operation of power electronic systems.

[0003] At present, traditional power semiconductor fault early warning mainly relies on single electrical parameter monitoring, such as threshold judgment of voltage or current. However, single parameter monitoring cannot comprehensively reflect the operating state of power semiconductors, which can easily lead to missed or false alarms, reducing the accuracy of fault early warning.

[0004] Although the above method can realize power semiconductor fault early warning, it lacks monitoring of factors such as temperature changes of power semiconductors when performing power semiconductor fault early warning, resulting in poor reliability and low accuracy of fault early warning. Therefore, how to improve the accuracy and reliability of power semiconductor fault early warning has become a problem to be solved. SUMMARY

[0005] The present application provides a power semiconductor fault early warning method and computer readable storage medium based on data driving, which mainly aims to improve the accuracy and reliability of power semiconductor fault early warning.

[0006] To achieve the above purpose, the present application provides a power semiconductor fault early warning method based on data driving, which comprises:

[0007] Receiving a power semiconductor fault early warning instruction, and confirming a fault early warning system based on the fault early warning instruction, wherein the fault early warning system comprises an electrical parameter monitoring unit, a frequency monitoring unit and a temperature monitoring unit, wherein the frequency monitoring unit comprises a low-frequency monitoring module and a high-frequency monitoring module;

[0008] Based on the power semiconductor, an electrical evaluation node is obtained, wherein the electrical evaluation node comprises a standard voltage, a standard current, a voltage early warning deviation value interval and a current early warning deviation value interval;

[0009] obtaining, based on a preset electrical monitoring period, a preset electrical monitoring time interval, and the electrical parameter monitoring unit, an electrical parameter node set, wherein the electrical parameter node set includes a plurality of electrical parameter nodes, and each electrical parameter node includes a monitored voltage and a monitored current;

[0010] obtaining, by using the low-frequency monitoring module and the high-frequency monitoring module, a frequency evaluation ratio, and confirming, based on the electrical parameter node set, the frequency evaluation ratio, and an electrical evaluation node, a first monitoring state of the power semiconductor, wherein the first monitoring state is a first early warning state or another first state;

[0011] when it is confirmed that the first monitoring state is the first early warning state, obtaining, based on a temperature monitoring unit, a temperature monitoring module set, and obtaining, by using the temperature monitoring module set, a monitored temperature set and a temperature change rate set, wherein the temperature monitoring module set includes a plurality of temperature monitoring modules, the monitored temperature set includes a plurality of monitored temperature values, and the temperature monitoring modules and the monitored temperature values are in one-to-one correspondence;

[0012] obtaining a comprehensive monitored temperature value based on the monitored temperature set and a pre-constructed temperature calculation formula;

[0013] confirming, based on the comprehensive monitored temperature value and the temperature change rate set, a second monitoring state of the power semiconductor, and realizing failure early warning of the power semiconductor, wherein the second monitoring state is a second early warning state or another second state.

[0014] Optionally, the electrical evaluation node is obtained based on the power semiconductor, and includes:

[0015] obtaining a standard voltage and a standard current of the power semiconductor;

[0016] obtaining a voltage allowable deviation value and a voltage failure deviation value of the power semiconductor;

[0017] obtaining a voltage early warning deviation value interval based on the voltage allowable deviation value and the voltage failure deviation value, wherein the minimum value and the maximum value corresponding to the voltage early warning deviation value interval are the voltage allowable deviation value and the voltage failure deviation value, respectively;

[0018] obtaining a current allowable deviation value and a current failure deviation value of the power semiconductor;

[0019] obtaining a current early warning deviation value interval based on the current allowable deviation value and the current failure deviation value, wherein the minimum value and the maximum value corresponding to the current early warning deviation value interval are the current allowable deviation value and the current failure deviation value, respectively;

[0020] associating the standard voltage, the standard current, the voltage early warning deviation value interval, and the current early warning deviation value interval to obtain the electrical evaluation node.

[0021] Optionally, the frequency evaluation ratio is obtained by the low-frequency monitoring module and the high-frequency monitoring module, comprising:

[0022] A frequency monitoring period is obtained, and a plurality of frequency monitoring sub-periods are obtained based on the frequency monitoring period;

[0023] The plurality of frequency monitoring sub-periods are sorted in the order of time from the front to the back corresponding to the frequency monitoring sub-periods, and a frequency monitoring sub-period sequence is obtained;

[0024] A plurality of odd frequency monitoring sub-periods and a plurality of even frequency monitoring sub-periods are obtained based on the frequency monitoring sub-period sequence, wherein the odd frequency monitoring sub-period is the frequency monitoring sub-period sequence with an odd number of bits, and the even frequency monitoring sub-period is the frequency monitoring sub-period sequence with an even number of bits.

[0025] A first frequency value set is obtained based on the plurality of odd frequency monitoring sub-periods, a preset first monitoring number and the low-frequency monitoring module;

[0026] The first frequency value set is summarized to obtain a plurality of first frequency value sets;

[0027] A second frequency value set is obtained based on the plurality of even frequency monitoring sub-periods, a preset second monitoring number and the high-frequency monitoring module;

[0028] The second frequency value set is summarized to obtain a plurality of second frequency value sets;

[0029] The frequency evaluation ratio is obtained based on the plurality of first frequency value sets, the plurality of second frequency value sets and a preset method.

[0030] Optionally, the power semiconductor one-level monitoring state is confirmed based on the electrical parameter node set, the frequency evaluation ratio and the electrical evaluation node, comprising:

[0031] The electrical parameter nodes in the electrical parameter node set are sorted in the order of time from the front to the back corresponding to the electrical parameter nodes, and an electrical parameter node sequence is obtained;

[0032] The electrical parameter nodes are extracted from the electrical parameter node sequence in turn, and a reference electrical parameter node is confirmed in the electrical parameter node sequence according to the extracted electrical parameter node, wherein the reference electrical parameter node is adjacent to the extracted electrical parameter node and lags behind the extracted electrical parameter node;

[0033] The absolute difference between the monitoring voltage in the electrical parameter node and the monitoring voltage in the reference electrical parameter node is calculated, and the absolute difference is taken as the voltage fluctuation difference;

[0034] The voltage fluctuation difference is compared with a preset voltage fluctuation threshold;

[0035] If the difference between the voltage fluctuation values is greater than the voltage fluctuation threshold value, the monitoring voltage corresponding to the reference electrical parameter node is confirmed as a fluctuation voltage;

[0036] The fluctuation voltages are summarized to obtain a fluctuation voltage set, and the number of fluctuation voltages in the fluctuation voltage set is counted to obtain a fluctuation voltage number;

[0037] The number of electrical parameter nodes in the sequence of electrical parameter nodes is counted to obtain a total number of electrical parameter nodes;

[0038] Based on the fluctuation voltage number, the total number of electrical parameter nodes, and a preset initial weight node, a weight node is obtained, wherein the initial weight node includes an initial first weight, an initial second weight, and an initial third weight, and the weight node includes a first weight, a second weight, and a third weight;

[0039] Based on the sequence of electrical parameter nodes, the fluctuation voltage number, the electrical evaluation node, the weight node, and a pre-constructed evaluation value calculation formula, a first evaluation value is obtained;

[0040] Based on the set of electrical parameter nodes and the electrical evaluation node, a second evaluation value is obtained;

[0041] The first evaluation value and a preset first warning threshold value, the second evaluation value and a preset second warning threshold value, and a frequency evaluation ratio and a preset frequency evaluation ratio threshold value are compared respectively;

[0042] If the first evaluation value is greater than the first warning threshold value, or the second evaluation value is greater than the second warning threshold value, or the frequency evaluation ratio is greater than the frequency evaluation ratio threshold value, a first-level monitoring state of the power semiconductor is confirmed as a first-level warning state;

[0043] Otherwise, the first-level monitoring state of the power semiconductor is confirmed as another first-level state.

[0044] Optionally, the weight node is obtained based on the fluctuation voltage number, the total number of electrical parameter nodes, and the preset initial weight node, including:

[0045] A ratio of the fluctuation voltage number to the total number of electrical parameter nodes is calculated to obtain a voltage ratio;

[0046] The voltage ratio and a preset ratio threshold value are compared;

[0047] If the voltage ratio is less than or equal to the ratio threshold value, the initial weight node is used as the weight node, otherwise, updated first weight, updated second weight, and updated third weight are obtained based on the fluctuation voltage number, the total number of electrical parameter nodes, and a pre-constructed update weight calculation formula;

[0048] The updated first weight and a minimum weight are compared;

[0049] If the updated first weight is greater than or equal to the minimum weight, the updated first weight, the updated second weight and the updated third weight are taken as the first weight, the second weight and the third weight respectively, otherwise, the minimum weight is taken as the updated first weight, and the first weight, the second weight and the third weight are obtained by using the updated first weight, the updated second weight, the updated third weight and a preset normalization method;

[0050] The first weight, the second weight and the third weight are summarized to obtain a weight node.

[0051] Optionally, the obtaining of the set of monitoring temperatures and the set of temperature change rates by using the set of temperature monitoring modules comprises:

[0052] The following operations are performed on each temperature monitoring module in the set of temperature monitoring modules:

[0053] An initial set of monitoring temperatures is obtained by using the temperature monitoring module, a preset temperature monitoring period and a preset temperature monitoring times, wherein the initial set of monitoring temperatures comprises a plurality of initial monitoring temperature values;

[0054] The initial set of monitoring temperatures is summarized to obtain a plurality of initial sets of monitoring temperatures, and each initial set of monitoring temperatures corresponds to a temperature monitoring module;

[0055] The following operations are performed on each initial set of monitoring temperatures in the plurality of initial sets of monitoring temperatures:

[0056] A monitoring temperature value obtaining scheme is constructed based on the initial set of monitoring temperatures, wherein the monitoring temperature value obtaining scheme is as follows:

[0057]

[0058] wherein T avg represents the monitoring temperature value, T i represents the i-th initial monitoring temperature value in the initial set of monitoring temperatures, T ak represents the k-th preset initial temperature abnormal value, and a represents a preset temperature threshold value, n represents the total number n of initial monitoring temperature values in the initial set of monitoring temperatures, and m represents the total number m of preset initial temperature abnormal values;

[0059] The monitoring temperature value is obtained based on the monitoring temperature value obtaining scheme.

[0060] After confirming that each temperature monitoring module obtains the corresponding monitoring temperature value, the monitoring temperature values are summarized to obtain a set of monitoring temperatures.

[0061] The set of temperature change rates is obtained based on the plurality of initial sets of monitoring temperatures.

[0062] Optionally, the obtaining of the set of temperature change rates based on the plurality of initial sets of monitoring temperatures comprises:

[0063] The following steps are performed on each of the plurality of initial monitoring temperature sets:

[0064] The initial monitoring temperature values in the initial monitoring temperature set are sorted in the order from the time corresponding to the acquisition of the initial monitoring temperature value to the time corresponding to the acquisition of the initial monitoring temperature value, to obtain an initial monitoring temperature sequence;

[0065] The temperature change rate is obtained based on the initial monitoring temperature sequence and a pre-constructed temperature change rate calculation formula;

[0066] The temperature change rates are summarized to obtain a temperature change rate set.

[0067] Optionally, the temperature calculation formula is as follows:

[0068]

[0069] wherein, T b represents the comprehensive monitoring temperature value, l represents that the monitoring temperature set has l monitoring temperature values, T j-avg represents the jth monitoring temperature value in the monitoring temperature set, w j represents the weight of the jth monitoring temperature value, R θjc represents the thermal resistance from the power semiconductor chip to the shell, and p represents the power consumption of the power semiconductor.

[0070] Optionally, the confirming the secondary monitoring state of the power semiconductor based on the comprehensive monitoring temperature value and the temperature change rate set comprises:

[0071] The following operations are performed on each of the temperature change rates in the temperature change rate set:

[0072] The absolute temperature change rate is obtained based on the temperature change rate, wherein the absolute temperature change rate is the absolute value of the temperature change rate;

[0073] The absolute temperature change rate is compared with a preset temperature change rate threshold value;

[0074] If the absolute temperature change rate is greater than the temperature change rate threshold value, the absolute temperature change rate is an unqualified absolute temperature change rate, otherwise, the absolute temperature change rate is a qualified absolute temperature change rate;

[0075] The unqualified absolute temperature change rates and the qualified absolute temperature change rates are summarized respectively to obtain an unqualified absolute temperature change rate set and a qualified absolute temperature change rate set;

[0076] The number of unqualified absolute temperature change rates in the unqualified absolute temperature change rate set and the number of qualified absolute temperature change rates in the qualified absolute temperature change rate set are counted respectively to obtain an unqualified number and a qualified number;

[0077] determine whether the comprehensive monitoring temperature value, the unqualified number and the qualified number satisfy a preset third verification condition;

[0078] confirm the secondary monitoring state of the power semiconductor as a secondary early warning state when the third verification condition is established;

[0079] Otherwise, the secondary monitoring state of the power semiconductor is confirmed as another secondary state.

[0080] To achieve the above-mentioned purpose, the application also provides a power semiconductor fault early warning system based on data driving, comprising:

[0081] An electrical parameter acquisition module is configured to receive a fault early warning instruction of a power semiconductor and confirm a fault early warning system based on the fault early warning instruction, wherein the fault early warning system comprises an electrical parameter monitoring unit, a frequency monitoring unit and a temperature monitoring unit, and the frequency monitoring unit comprises a low-frequency monitoring module and a high-frequency monitoring module.

[0082] An electrical evaluation node is obtained based on the power semiconductor, wherein the electrical evaluation node comprises a standard voltage, a standard current, a voltage early warning deviation value interval and a current early warning deviation value interval.

[0083] An electrical parameter node set is obtained based on a preset electrical monitoring time period, a preset electrical monitoring time interval and the electrical parameter monitoring unit, wherein the electrical parameter node set comprises a plurality of electrical parameter nodes, and each electrical parameter node comprises a monitoring voltage and a monitoring current.

[0084] A primary monitoring early warning module is configured to obtain a frequency evaluation ratio by using the low-frequency monitoring module and the high-frequency monitoring module, and confirm a primary monitoring state of the power semiconductor based on the electrical parameter node set, the frequency evaluation ratio and the electrical evaluation node, wherein the primary monitoring state is a primary early warning state or another primary state.

[0085] A comprehensive temperature acquisition module is configured to obtain a temperature monitoring module set based on the temperature monitoring unit when the primary monitoring state is confirmed as the primary early warning state, and obtain a monitoring temperature set and a temperature change rate set by using the temperature monitoring module set, wherein the temperature monitoring module set comprises a plurality of temperature monitoring modules, the monitoring temperature set comprises a plurality of monitoring temperature values, and the temperature monitoring modules and the monitoring temperature values are in one-to-one correspondence.

[0086] A comprehensive monitoring temperature value is obtained based on the monitoring temperature set and a pre-constructed temperature calculation formula.

[0087] A secondary monitoring early warning module is configured to confirm a secondary monitoring state of the power semiconductor based on the comprehensive monitoring temperature value and the temperature change rate set, and realize fault early warning of the power semiconductor, wherein the secondary monitoring state is a secondary early warning state or another secondary state.

[0088] To solve the above problems, the application further provides an electronic device, which comprises:

[0089] a memory, which stores at least one instruction; and a processor, which executes the instruction stored in the memory to realize the data-driven power semiconductor fault early warning method.

[0090] To solve the above problems, the application further provides a computer readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to realize the data-driven power semiconductor fault early warning method.

[0091] The application receives a failure early warning instruction of a power semiconductor, confirms a failure early warning system based on the failure early warning instruction, wherein the failure early warning system comprises an electrical parameter monitoring unit, a frequency monitoring unit and a temperature monitoring unit, the frequency monitoring unit comprises a low-frequency monitoring module and a high-frequency monitoring module, an electrical evaluation node is obtained based on the power semiconductor, the electrical evaluation node comprises a standard voltage, a standard current, a voltage early warning deviation value interval and a current early warning deviation value interval, and the electrical parameter allowable deviation value and the electrical parameter failure deviation value are respectively taken as the minimum value and the maximum value of the electrical parameter early warning deviation value interval, the range between the allowable deviation and the failure deviation is taken as the early warning range, the power semiconductor can be adjusted in time to ensure its stable operation when the deviation of the electrical parameter value exceeds the allowable range but has not reached the failure deviation value, an electrical parameter node set is obtained based on a preset electrical monitoring time interval, a preset electrical monitoring time interval and the electrical parameter monitoring unit, the electrical parameter node set comprises a plurality of electrical parameter nodes, each electrical parameter node comprises a monitoring voltage and a monitoring current, a frequency evaluation ratio is obtained by using the low-frequency monitoring module and the high-frequency monitoring module, a first-level monitoring state of the power semiconductor is confirmed based on the electrical parameter node set, the frequency evaluation ratio and the electrical evaluation node, the first-level monitoring state is a first-level early warning state or other first-level states, the low-frequency monitoring module (steady-state analysis) and the high-frequency monitoring module (transient-state analysis) are alternately sampled in time sequence, the steady-state frequency average and the transient-state frequency burst value are comprehensively considered, the blind area missed detection limitation caused by the fixed duty cycle phase in the traditional single sampling mode is broken through, the early warning reliability and accuracy are improved, the dynamic weight method is used to obtain the weights of the three indexes used to calculate the first evaluation value, the related weight of the voltage fluctuation frequency index is dynamically increased when the voltage proportion corresponding to the voltage fluctuation is larger, the key index influence is highlighted, and the potential failure risk is captured in time, after the first-level monitoring state is confirmed as the first-level early warning state, a temperature monitoring module set is obtained based on the temperature monitoring unit, a monitoring temperature set and a temperature change rate set are obtained by using the temperature monitoring module set, the temperature monitoring module set comprises a plurality of temperature monitoring modules, the monitoring temperature set comprises a plurality of monitoring temperature values, and the temperature monitoring module and the monitoring temperature value are one-to-one corresponding, the initial abnormal temperature value is identified and removed by using the monitoring temperature value obtaining scheme, the calculated monitoring temperature value is closer to the true situation, the accuracy and reliability of temperature monitoring are improved, the external temperature of the power semiconductor is provided by using the monitoring temperature value, the internal node temperature of the power semiconductor is calculated by using the thermal characteristic parameter and the power consumption, the temperature monitoring accuracy is improved by comprehensively considering the external temperature and the internal node temperature of the power semiconductor, a comprehensive monitoring temperature value is obtained based on the monitoring temperature set and a pre-constructed temperature calculation formula, a second-level monitoring state of the power semiconductor is confirmed based on the comprehensive monitoring temperature value and the temperature change rate set, and the failure early warning of the power semiconductor is realized.The secondary monitoring state is a secondary early warning state or other secondary state, and the application can evaluate the thermal state of the power semiconductor based on the comprehensive monitoring temperature value and temperature change rate set, accurately determine whether the power semiconductor is in a secondary early warning state through a second verification condition, and timely discover potential faults to improve the reliability and safety of the power semiconductor operation. Therefore, the application can improve the accuracy and reliability of power semiconductor fault early warning. BRIEF DESCRIPTION OF DRAWINGS

[0092] Figure 1 A flowchart of a data-driven power semiconductor fault early warning method according to an embodiment of the application is shown in FIG.

[0093] Figure 2 A functional module diagram of a data-driven power semiconductor fault early warning system according to an embodiment of the application is shown in FIG.

[0094] Figure 3 A structural diagram of an electronic device implementing the data-driven power semiconductor fault early warning method according to an embodiment of the application is shown in FIG.

[0095] REFERENCE SIGNS:

[0096] 1, electronic device; 10, processor; 11, storage; 12, bus.

[0097] The implementation, functional features and advantages of the application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0098] It should be understood that the specific embodiments described herein are merely intended to explain the application and are not intended to limit the application.

[0099] The embodiments of the application provide a data-driven power semiconductor fault early warning method. The execution subject of the data-driven power semiconductor fault early warning method includes but is not limited to at least one of electronic devices such as a server, a terminal, etc., which can be configured to execute the method provided by the embodiments of the application. In other words, the data-driven power semiconductor fault early warning method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0100] Referring to Figure 1 A flowchart of a data-driven power semiconductor fault early warning method according to an embodiment of the application is shown in FIG. In this embodiment, the data-driven power semiconductor fault early warning method includes:

[0101] S1, receive a failure warning instruction of the power semiconductor, and confirm a failure warning system based on the failure warning instruction, wherein the failure warning system comprises an electrical parameter monitoring unit, a frequency monitoring unit and a temperature monitoring unit, and the frequency monitoring unit comprises a low frequency monitoring module and a high frequency monitoring module.

[0102] It should be explained that the power semiconductor is a kind of semiconductor device for controlling and converting electric energy, which can realize effective transmission and conversion of electric energy, and the failure warning instruction is an instruction issued by personnel who want to realize failure warning of the power semiconductor. The failure warning system is an integrated unit for monitoring the running state of the power semiconductor by using the electrical parameter monitoring unit, the frequency monitoring unit and the temperature monitoring unit, wherein the failure warning system comprises the electrical parameter monitoring unit, the frequency monitoring unit and the temperature monitoring unit, and the frequency monitoring unit comprises the low frequency monitoring module and the high frequency monitoring module. For the application of specific units and modules, please refer to the subsequent embodiments.

[0103] S2, obtain an electrical evaluation node based on the power semiconductor, wherein the electrical evaluation node comprises a standard voltage, a standard current, a voltage warning deviation value interval and a current warning deviation value interval.

[0104] It should be explained that the electrical evaluation node is obtained based on the power semiconductor, which comprises:

[0105] obtaining the standard voltage and the standard current of the power semiconductor;

[0106] obtaining the voltage allowable deviation value and the voltage failure deviation value of the power semiconductor;

[0107] obtaining the voltage warning deviation value interval based on the voltage allowable deviation value and the voltage failure deviation value, wherein the minimum value and the maximum value corresponding to the voltage warning deviation value interval are the voltage allowable deviation value and the voltage failure deviation value respectively;

[0108] obtaining the current allowable deviation value and the current failure deviation value of the power semiconductor;

[0109] obtaining the current warning deviation value interval based on the current allowable deviation value and the current failure deviation value, wherein the minimum value and the maximum value corresponding to the current warning deviation value interval are the current allowable deviation value and the current failure deviation value respectively;

[0110] associating the standard voltage, the standard current, the voltage warning deviation value interval and the current warning deviation value interval to obtain the electrical evaluation node.

[0111] It can be understood that the standard voltage and the standard current respectively refer to the rated voltage and the rated current of the power semiconductor, the voltage allowable deviation value refers to the maximum allowable deviation value of the actual voltage of the power semiconductor relative to the standard voltage in a stable working state, the current allowable deviation value refers to the maximum allowable deviation value of the actual current of the power semiconductor relative to the standard current in a stable working state, and the voltage allowable deviation value and the current allowable deviation value both belong to the allowable fluctuation range of the power semiconductor in normal working state, and will not cause performance degradation or damage of the power semiconductor. The voltage fault deviation value and the current fault deviation value refer to the difference value between the actual voltage and the standard voltage and the difference value between the actual current and the standard current of the power semiconductor in a fault state, and when the difference value between the actual voltage and the standard voltage exceeds the voltage fault deviation value or the difference value between the actual current and the standard current exceeds the current fault deviation value, it indicates that the power semiconductor is in a fault state. The voltage early warning deviation value interval refers to the transition interval of the deviation between the actual voltage and the standard voltage of the power semiconductor in the working process, and the current early warning deviation value interval refers to the transition interval of the deviation between the actual current and the standard current of the power semiconductor in the working process.

[0112] For example, if the standard voltage of a certain power semiconductor is 100V, the voltage allowable deviation value is 5V, and the voltage fault deviation value is 15V, it is indicated that the actual voltage within the range of [95V, 105V] is in a safe range, the actual voltage greater than 115V or less than 85V is in a fault range, and the actual voltage within the range of [85V, 95V] and [105V, 115V] is in a pre-warning range. At this time, the working state of the power semiconductor has approached the fault edge, and measures can be taken in advance to avoid equipment damage or performance degradation before the fault occurs. At this time, the corresponding voltage early warning deviation value interval is [5V, 15V]. Similarly, if the standard current of a certain power semiconductor is 50A, the current allowable deviation value is 2A, and the current fault deviation value is 5A, it is indicated that the actual current within the range of [48A, 52A] is in a safe range, the actual current greater than 55A or less than 45A is in a fault range, and the actual current within the range of [45A, 48A] and [52A, 55A] is in a pre-warning range. At this time, the corresponding current early warning deviation value interval is [2A, 5A], and thus the electrical evaluation node is {100V-(5V, 15V), 50A-(2A, 5A)}. The electrical parameter allowable deviation value and the electrical parameter fault deviation value are respectively taken as the minimum value and the maximum value of the electrical parameter early warning deviation value interval, and the range between the allowable deviation and the fault deviation is taken as the pre-warning range, so that the power semiconductor can be adjusted in time to ensure stable operation when it is monitored that the deviation of the electrical parameter value exceeds the allowable range but has not reached the fault deviation value.

[0113] S3, obtaining electrical parameter node set based on preset electrical monitoring time period, preset electrical monitoring time interval and the electrical parameter monitoring unit, wherein the electrical parameter node set comprises a plurality of electrical parameter nodes, and each electrical parameter node comprises monitored voltage and monitored current.

[0114] It can be understood that the electrical parameter monitoring unit is used to collect voltage signal and current signal as monitored voltage and monitored current in real time. Optionally, voltage sensor and current sensor are used as the fault detection unit to collect voltage signal and current signal. The monitored voltage and monitored current represent actual voltage and actual current of the power semiconductor during operation.

[0115] For example, it is assumed that the electrical monitoring time period is from 8:00:00 to 8:01:40 on a certain day, and the electrical monitoring time interval is 2 seconds. Therefore, the electrical parameter monitoring times are 50 times. Voltage sensor and current sensor of the electrical parameter monitoring unit are used to collect voltage signal and current signal every 2 seconds between 8:00:00 and 8:01:40 on the certain day, and 50 groups of monitored voltage and 50 groups of monitored current are obtained. Only 10 groups of monitored voltage and 10 groups of monitored current are taken as an example. The electrical parameter node set obtained from the 10 groups of monitored voltage and the 10 groups of monitored current is {(8:00:02, 99V, 50A), (8:00:04, 103V, 51A), (8:00:06, 103V, 51A), (8:00:08, 102V, 50A), (8:00:10, 98V, 48A), (8:00:12, 99V, 49A), (8:00:14, 101V, 51A), (8:00:16, 99V, 49A), (8:00:18, 97V, 47A), (8:00:20, 100V, 50A)}.

[0116] S4, obtaining frequency evaluation ratio by using the low-frequency monitoring module and the high-frequency monitoring module, and confirming the first monitoring state of the power semiconductor based on the electrical parameter node set, the frequency evaluation ratio and the electrical evaluation node, wherein the first monitoring state is a first early warning state or other first state.

[0117] It can be understood that the first early warning state is a state in which the power semiconductor has potential risks but has not reached the failure range during the first monitoring, and the other first state means other states of the power semiconductor during the first monitoring except the first early warning state.

[0118] In detail, the obtaining of the frequency evaluation ratio by using the low-frequency monitoring module and the high-frequency monitoring module comprises:

[0119] obtaining a frequency monitoring time period, and obtaining a plurality of frequency monitoring sub-periods based on the frequency monitoring time period;

[0120] The plurality of frequency monitoring sub-periods are sorted in a time sequence from front to back corresponding to the frequency monitoring sub-periods, to obtain a frequency monitoring sub-period sequence;

[0121] Based on the frequency monitoring sub-period sequence, a plurality of odd frequency monitoring sub-periods and a plurality of even frequency monitoring sub-periods are obtained, wherein the odd frequency monitoring sub-period is a frequency monitoring sub-period with an odd position sequence in the frequency monitoring sub-period sequence, and the even frequency monitoring sub-period is a frequency monitoring sub-period with an even position sequence in the frequency monitoring sub-period sequence;

[0122] Based on the plurality of odd frequency monitoring sub-periods, a preset first monitoring number and a low frequency monitoring module, a first frequency value set is obtained;

[0123] The first frequency value set is summarized to obtain a plurality of first frequency value sets;

[0124] Based on the plurality of even frequency monitoring sub-periods, a preset second monitoring number and a high frequency monitoring module, a second frequency value set is obtained;

[0125] The second frequency value set is summarized to obtain a plurality of second frequency value sets;

[0126] Based on the plurality of first frequency value sets, the plurality of second frequency value sets and a preset method, a frequency evaluation ratio is obtained.

[0127] For example, assuming that the frequency monitoring period is from 8:00:00 to 8:00:30 on a certain day, each frequency monitoring sub-period is 5 seconds, and the corresponding multiple frequency monitoring sub-periods are 8:00:00-8:00:05, 8:00:05-8:00:10, 8:00:10-8:00:15, 8:00:15-8:00:20, 8:00:20-8:00:25, and 8:00:25-8:00:30, the corresponding frequency monitoring sub-period sequence is represented as {8:00:00-8:00:05, 8:00:05-8:00:10, 8:00:10-8:00:15, 8:00:15-8:00:20, 8:00:20-8:00:25, 8:00:25-8:00:30}, the corresponding multiple odd frequency monitoring sub-periods are {8:00:00-8:00:05, 8:00:10-8:00:15, 8:00:20-8:00:25}, the corresponding multiple even frequency monitoring sub-periods are {8:00:05-8:00:10, 8:00:15-8:00:20, 8:00:25-8:00:30}, and taking the odd frequency monitoring sub-period 8:00:00-8:00:05 as an example: in the period from 8:00:00 to 8:00:05, the frequency signal is collected by using the low-frequency monitoring module, if the first monitoring number is 500, then the first frequency value set corresponding to the odd frequency monitoring sub-period contains 500 first frequency values, each odd frequency monitoring sub-period corresponds to a first frequency value set, and similarly, taking the even frequency monitoring sub-period 8:00:05-8:00:10 as an example: in the period from 8:00:05 to 8:00:10, the frequency signal is collected by using the high-frequency monitoring module, if the second monitoring number is 5000, then the second frequency value set corresponding to the even frequency monitoring sub-period contains 5000 second frequency values, and each even frequency monitoring sub-period corresponds to a second frequency value set. In general, in the actual monitoring process, multiple groups of frequency monitoring sub-periods can be divided according to the frequency monitoring period to facilitate the collection of more frequency signals for early warning analysis, and in this example, only six groups of frequency monitoring sub-periods are taken as examples for explanation.

[0128] It should be understood that the low-frequency monitoring module and the high-frequency monitoring module are both components in the frequency monitoring unit for frequency signal acquisition. The difference is that the low-frequency monitoring module acquires frequency signals less frequently (e.g., several times or dozens of times per second) within the corresponding monitoring sub-period, while the high-frequency monitoring module acquires frequency signals more frequently (e.g., thousands of times per second or even at the MHz level) within the corresponding monitoring sub-period. Optionally, frequency signal acquisition can be achieved by using a low-speed, high-precision ADC (e.g., ADS1115) and a high-speed ADC (e.g., ADS8881) as the low-frequency monitoring module and the high-frequency monitoring module, respectively. This is prior art and will not be elaborated on here. The process of obtaining the frequency evaluation ratio based on multiple first frequency value sets, multiple second frequency value sets and a preset method is as follows: assuming that the normal range of the switching frequency of a power semiconductor is 18KHz-22KHz, 3 first frequency value sets and 3 second frequency value sets are obtained from the above example. First, take one of the first frequency value sets as an example: take the average of all first frequency values ​​in the first frequency value set, and judge the relationship between the average and the normal range of the switching frequency of 18KHz-22KHz. If the average is not within the range of 18KHz-22KHz, the first frequency value set is regarded as a warning first frequency value set. Secondly, take one of the second frequency value sets as an example: if there is a second frequency value in the second frequency value set that exceeds the range of 18KHz-22KHz, the second frequency value set is regarded as a warning second frequency value set. After the 3 first frequency value sets and 3 second frequency value sets are confirmed, calculate the ratio of [(the total number of all warning first frequency value sets + the total number of all warning second frequency value sets) / (the total number of all first frequency value sets + the total number of all second frequency value sets)], and use this ratio as the frequency evaluation ratio. The embodiment of the present invention uses the time-series alternating sampling of the low-frequency monitoring module (steady-state analysis) and the high-frequency monitoring module (transient analysis), comprehensively considering the steady-state frequency mean and the transient frequency burst value, breaking through the blind spot missed detection limitation caused by the fixed duty cycle phase in the traditional single sampling mode, and improving the warning reliability and accuracy.

[0129] It should be explained that the confirmation of the primary monitoring status of the power semiconductor based on the electrical parameter node set, the frequency evaluation ratio and the electrical evaluation node includes:

[0130] Sort the electrical parameter nodes in the electrical parameter node set according to the time corresponding to the electrical parameter nodes from front to back to obtain an electrical parameter node sequence;

[0131] Extracting electrical parameter nodes sequentially from the electrical parameter node sequence, and identifying a reference electrical parameter node in the electrical parameter node sequence based on the extracted electrical parameter nodes, wherein the reference electrical parameter node is adjacent to the extracted electrical parameter node and lags behind the extracted electrical parameter node;

[0132] an absolute difference value between the monitored voltage in the electrical parameter node and the monitored voltage in the reference electrical parameter node is calculated as a voltage fluctuation difference value;

[0133] the voltage fluctuation difference value is compared with a preset voltage fluctuation threshold value;

[0134] if the voltage fluctuation difference value is greater than the voltage fluctuation threshold value, the monitored voltage corresponding to the reference electrical parameter node is confirmed as a fluctuation voltage;

[0135] the fluctuation voltages are summarized to obtain a fluctuation voltage set, and the number of fluctuation voltages in the fluctuation voltage set is counted to obtain a fluctuation voltage number;

[0136] the number of electrical parameter nodes in the electrical parameter node sequence is counted to obtain a total number of electrical parameter nodes;

[0137] an initial weight node is obtained based on the fluctuation voltage number, the total number of electrical parameter nodes and a preset initial weight node, wherein the initial weight node includes an initial first weight, an initial second weight and an initial third weight, and the weight node includes a first weight, a second weight and a third weight;

[0138] a first evaluation value is obtained based on the electrical parameter node sequence, the fluctuation voltage number, the electrical evaluation node, the weight node and a preset evaluation value calculation formula, wherein the evaluation value calculation formula is as follows:

[0139]

[0140] wherein S v represents the first evaluation value, e represents the total number of electrical parameter nodes, V k and V k-1 represent the monitored voltage corresponding to the kth electrical parameter node and the k-1th electrical parameter node in the electrical parameter node sequence respectively, d v represents the fluctuation voltage number, a1'', a2'' and a3'' represent the first weight, the second weight and the third weight in the weight node respectively, V std represents the standard voltage;

[0141] a second evaluation value is obtained based on the electrical parameter node set and the electrical evaluation node;

[0142] the first evaluation value and a preset first warning threshold value, the second evaluation value and a preset second warning threshold value, and the frequency evaluation ratio and a preset frequency evaluation ratio threshold value are compared respectively;

[0143] if the first evaluation value is greater than the first warning threshold value, or the second evaluation value is greater than the second warning threshold value, or the frequency evaluation ratio is greater than the frequency evaluation ratio threshold value, the primary monitoring state of the power semiconductor is confirmed as a primary warning state;

[0144] Otherwise, the primary monitoring state of the power semiconductor is confirmed as the other primary state.

[0145] It can be understood that the electrical parameter node sequence based on the above electrical parameter node set is {(8:00:02, 99V, 50A), (8:00:04, 103V, 51A), (8:00:06, 103V, 51A), (8:00:08, 102V, 50A), (8:00:10, 98V, 48A), (8:00:12, 99V, 49A), (8:00:14, 101V, 51A), (8:00:16, 99V, 49A), (8:00:18, 97V, 47A), (8:00:20, 100V, 50A)}, taking the first electrical parameter node as an example: the electrical parameter node (8:00:02, 99V, 51A) is extracted from the electrical parameter node sequence, and the corresponding reference electrical parameter node is (8:00:04, 96V, 49A). The absolute difference between the monitoring voltage 99V in the electrical parameter node and the monitoring voltage 103V in the reference electrical parameter node is 4V, and 4V is the voltage fluctuation difference. If the preset voltage fluctuation threshold is 2.5V, the voltage fluctuation difference 4V is greater than the voltage fluctuation threshold 2.5V, and the monitoring voltage 103V corresponding to the electrical parameter node (8:00:04, 103V, 51A) is a fluctuating voltage. Thus, the electrical parameter nodes corresponding to all fluctuating voltages are (8:00:04, 103V, 51A), (8:00:10, 98V, 48A), and (8:00:20, 100V, 50A), and the number of corresponding fluctuating voltages is 3, and the total number of electrical parameter nodes is 10. In general, the voltage fluctuation threshold can refer to the voltage allowable deviation value. Generally, the voltage fluctuation threshold is set to between 40% and 60% of the voltage allowable deviation value, which can accurately capture the voltage fluctuation caused by the abnormality. In the example, the voltage allowable deviation value is 5V, so the voltage fluctuation threshold can be set to between 2V and 3V.

[0146] It should be understood that the first evaluation value is obtained by using the electrical parameter node sequence, the number of fluctuating voltages, the electrical evaluation node, the weight node and the pre-constructed evaluation value calculation formula, the first evaluation value is a quantitative value for evaluating whether the power semiconductor reaches a first warning state based on the voltage monitoring angle, and is used for comparison with the first warning threshold to judge the first warning state, the first warning threshold is a reference quantitative value for judging the warning state based on the voltage monitoring angle, and the acquisition process of the first warning threshold can be referred to as follows: a plurality of actual voltage values are collected when the power semiconductor is in a normal working state, a plurality of electrical node sequences corresponding to the plurality of actual voltage values are obtained, and the evaluation value under the normal working state can be obtained by using the evaluation value calculation formula, a plurality of evaluation values can be obtained by collecting multiple times, and the average of the plurality of evaluation values is taken as the first warning threshold. Similarly, the second evaluation value is a quantitative value for evaluating whether the power semiconductor reaches a first warning state based on the current monitoring angle, and is used for comparison with the second warning threshold to judge the first warning state, and the second warning threshold is a reference quantitative value for judging the warning state based on the current monitoring angle. The acquisition process of the second evaluation value and the second warning threshold is the same as that of the first evaluation value and the first warning threshold, and will not be described here. The frequency evaluation ratio is a quantitative ratio for evaluating whether the power semiconductor reaches a first warning state based on the frequency monitoring angle, and the frequency evaluation ratio threshold is a reference ratio for comparison with the frequency evaluation ratio.

[0147] It can be understood that the acquisition process of the first evaluation value is as follows: the evaluation value calculation formula obtains the first evaluation value by three indexes of voltage absolute deviation, voltage relative fluctuation and voltage fluctuation frequency, and gives each index a corresponding weight, wherein the voltage absolute deviation is used to evaluate the overall deviation degree of the monitoring voltage corresponding to all electrical parameter nodes from the standard voltage V std , the voltage relative fluctuation is used to represent the instantaneous voltage change rate of the monitoring voltage corresponding to the detection electrical parameter node, and the voltage fluctuation frequency is used to reflect the intensive degree of abnormal monitoring voltage fluctuation, wherein the weights of the three indexes are obtained by a dynamic weight method.

[0148] Further, the weight node is obtained based on the number of fluctuating voltages, the total number of electrical parameter nodes and the preset initial weight node, including:

[0149] The ratio of the number of fluctuating voltages to the total number of electrical parameter nodes is calculated to obtain a voltage ratio;

[0150] The voltage ratio is compared with the preset ratio threshold;

[0151] If the voltage ratio is less than or equal to the ratio threshold, the initial weight nodes are used as weight nodes, otherwise, updated first weight, updated second weight and updated third weight are obtained based on the number of fluctuation voltages, the total number of electrical parameter nodes and a pre-constructed update weight calculation formula, wherein the update weight calculation formula is as follows:

[0152]

[0153] a1' = 1 - a3' - a2'

[0154] wherein a1, a2 and a3 represent initial first weight, initial second weight and initial third weight respectively, a1', a2' and a3' represent updated first weight, updated second weight and updated third weight respectively, a min represents a preset minimum weight;

[0155] The updated first weight is compared with the minimum weight.

[0156] If the updated first weight is greater than or equal to the minimum weight, the updated first weight, the updated second weight and the updated third weight are used as the first weight, the second weight and the third weight respectively, otherwise, the minimum weight is used as the updated first weight, and the first weight, the second weight and the third weight are obtained by using the updated first weight, the updated second weight, the updated third weight and a preset normalization method.

[0157] The first weight, the second weight and the third weight are summarized to obtain the weight nodes.

[0158] For example, assuming that the ratio threshold is 1 / 2, if the ratio of the number of fluctuation voltages to the total number of electrical parameter nodes, i.e. the voltage ratio, is 3 / 10, the initial weight nodes are 0.25, 0.45 and 0.3 respectively, and the minimum weight a min is 0.1, at this time, the voltage ratio 3 / 10 is less than the ratio threshold 1 / 2, the initial weight nodes are used as the weight nodes, i.e. the first weight, the second weight and the third weight are 0.25, 0.45 and 0.3 respectively, if the voltage ratio is 6 / 10 which is greater than the voltage ratio 3 / 10, at this time, the updated first weight, the updated second weight and the updated third weight are obtained by using the update weight calculation formula, and the obtaining process is as follows: first, the updated third weight a1' is calculated to be 0.45 which is greater than or equal to 0.1 (a min ), then the updated second weight is calculated to be 0.15 which is greater than or equal to 0.1 (a min ), and finally the updated first weight is calculated to be 0.4, thus it can be concluded that the updated first weight is greater than or equal to the minimum weight 0.1 (a min), so the first weight, the second weight and the third weight are respectively updated first weight 0.4, updated second weight 0.15 and updated third weight 0.45. Assuming that the updated first weight is less than the minimum weight 0.1 (a min ), considering that a3'+a2' may be greater than 1, the obtained updated first weight is negative, the updated first weight, the updated second weight and the updated third weight are normalized to [0.1] by using the Min-Max normalization method, and the normalized updated first weight, the normalized updated second weight and the normalized updated third weight are respectively taken as the updated first weight, the updated second weight and the updated third weight. The embodiment of the application uses a dynamic weight method to obtain the weights corresponding to the three indexes used for calculating the first evaluation value, when the voltage fluctuation corresponds to a relatively large voltage proportion, the related weight of the voltage fluctuation frequency index is dynamically increased, the key index influence is highlighted, and the potential fault risk is captured in time.

[0159] S5, when confirming that the first-level monitoring state is the first-level early warning state, acquiring a temperature monitoring module set based on the temperature monitoring unit, and acquiring a monitoring temperature set and a temperature change rate set by using the temperature monitoring module set, wherein the temperature monitoring module set comprises a plurality of temperature monitoring modules, the monitoring temperature set comprises a plurality of monitoring temperature values, and the temperature monitoring module and the monitoring temperature value are in one-to-one correspondence.

[0160] It should be explained that the temperature monitoring module set is used to acquire the monitoring temperature set and the temperature change rate set, including:

[0161] The following operations are performed on each temperature monitoring module in the temperature monitoring module set:

[0162] An initial monitoring temperature set is acquired by using the temperature monitoring module, the preset temperature monitoring period and the preset temperature monitoring times, wherein the initial monitoring temperature set comprises a plurality of initial monitoring temperature values;

[0163] The initial monitoring temperature sets are summarized to obtain a plurality of initial monitoring temperature sets, and the initial monitoring temperature set and the temperature monitoring module are in one-to-one correspondence;

[0164] The following operations are performed on each initial monitoring temperature set in the plurality of initial monitoring temperature sets:

[0165] A monitoring temperature value acquisition scheme is constructed based on the initial monitoring temperature set, wherein the monitoring temperature value acquisition scheme is as follows:

[0166]

[0167] Wherein, T avg represents the monitoring temperature value, T i represents the i-th initial monitoring temperature value in the initial monitoring temperature set, and T akrepresents the preset kth initial temperature abnormal value, a represents the preset temperature threshold value, n represents that there are n initial monitoring temperature values in the initial monitoring temperature set, and m represents that there are m preset initial temperature abnormal values;

[0168] obtaining the monitoring temperature value based on the monitoring temperature value obtaining scheme;

[0169] After confirming that each temperature monitoring module obtains the corresponding monitoring temperature value, the monitoring temperature values are summarized to obtain a monitoring temperature set.

[0170] The temperature change rate set is obtained based on the plurality of initial monitoring temperature sets.

[0171] It should be understood that the temperature monitoring unit is composed of a plurality of temperature monitoring modules, which are used to collect temperature values near the power semiconductor, and the temperature values are initial monitoring temperature values. The initial monitoring temperature values are temperature values near the power semiconductor measured by the temperature monitoring module, which reflect the external temperature of the power semiconductor under actual working conditions. Optionally, the collection of the initial monitoring temperature values can be realized by using a DS18B20 intelligent temperature sensor as the temperature monitoring module.

[0172] For example, assuming that the temperature monitoring unit is composed of 5 temperature monitoring modules, and taking one of the temperature monitoring modules as an example: if the temperature monitoring period is 10 minutes and the temperature monitoring times are 10, the temperature detection module collects the temperature every 1 minute in the monitoring period to obtain 10 initial monitoring temperature values, and the initial monitoring temperature set corresponding to the temperature detection module is composed of the 10 initial monitoring temperature values. If the preset temperature threshold value is 2℃ and the initial monitoring temperature set is {30℃, 32℃, 31℃, 32℃, 30℃, 35℃, 31℃, 32℃, 32℃, 30℃}, the monitoring temperature value obtaining scheme is constructed based on the initial monitoring temperature set, and the implementation process of the monitoring temperature value obtaining scheme is as follows: the average temperature of all initial monitoring temperature values in the initial monitoring temperature set is calculated as 31.5℃, the initial monitoring temperature value deviating from the average temperature 31.5℃ by more than 2℃ is regarded as an initial temperature abnormal value, that is, the initial monitoring temperature value not belonging to the temperature interval [29.5℃, 33.5℃] is regarded as an initial temperature abnormal value, and in this example, the initial monitoring temperature value 35℃ does not belong to the temperature interval [29.5℃, 33.5℃], so the initial monitoring temperature value 35℃ is removed from the initial monitoring temperature set, and the average of the remaining initial monitoring temperature values in the initial monitoring temperature set after removing the initial monitoring temperature value 35℃ is taken as the monitoring temperature value corresponding to the temperature monitoring module. After confirming that the 5 temperature monitoring modules obtain the corresponding monitoring temperature values, the 5 monitoring temperature values are summarized to obtain a monitoring temperature set. The initial abnormal temperature value is identified and removed by using the monitoring temperature value obtaining scheme, so that the calculated monitoring temperature value is closer to the actual situation, and the accuracy and reliability of temperature monitoring are improved.

[0173] In detail, the obtaining of the temperature change rate set based on the plurality of initial monitoring temperature sets comprises:

[0174] The following steps are performed on each initial monitoring temperature set in the plurality of initial monitoring temperature sets:

[0175] The initial monitoring temperature values in the initial monitoring temperature set are sorted in the order from the time corresponding to the initial monitoring temperature value to the rear, to obtain an initial monitoring temperature sequence.

[0176] The temperature change rate is obtained based on the initial monitoring temperature sequence and a pre-constructed temperature change rate calculation formula, wherein the temperature change rate calculation formula is as follows:

[0177]

[0178] wherein ΔT represents the temperature change rate, T g+1 represents the (g+1)th initial monitoring temperature value in the initial monitoring temperature sequence, T g represents the gth initial monitoring temperature value in the initial monitoring temperature sequence, and Δt' represents the time interval between the adjacent two initial monitoring temperature values in the initial monitoring temperature sequence, and the time interval is related to the temperature monitoring times;

[0179] The temperature change rates are summarized to obtain a temperature change rate set.

[0180] It can be understood that the temperature change rate is a change rate threshold set by a person, which is used to measure the change degree of the power semiconductor accessory temperature value in the temperature monitoring period, the temperature change rate calculation formula calculates the change between the adjacent initial monitoring temperature values in the initial monitoring temperature sequence, and the comprehensive temperature change rate is obtained by combining the time interval, which comprehensively considers the absolute change amount of the temperature, the rate of the temperature change, and the relative size of the temperature change.

[0181] For example, Δt' is the time interval between the adjacent two initial monitoring temperature values in the initial monitoring temperature sequence. Assuming that the temperature monitoring period is from 8:10:00 to 8:20:00 in the morning of a certain day, and the temperature monitoring times are 10 times, the temperature is collected every 1 minute, that is, the initial monitoring temperature values are collected at 8:11:00, 8:12:00, 8:13:00, 8:14:00, 8:15:00, 8:16:00, 8:17:00, 8:18:00, 8:19:00, and 8:20:00, respectively, and therefore the time interval Δt' between the adjacent two initial monitoring temperature values in the corresponding initial monitoring temperature sequence is 1 minute.

[0182] S6, obtaining a comprehensive monitoring temperature value based on the monitoring temperature set and a pre-constructed temperature calculation formula.

[0183] It should be explained that the temperature calculation formula is as follows:

[0184]

[0185] Wherein, T b represents the comprehensive monitoring temperature value, l represents the total number of monitoring temperature values in the monitoring temperature set, T j-avg represents the jth monitoring temperature value in the monitoring temperature set, w j represents the weight of the jth monitoring temperature value, R θjc represents the thermal resistance of the power semiconductor chip to the shell, and p represents the power consumption of the power semiconductor.

[0186] It can be understood that the comprehensive monitoring temperature value is a temperature index calculated by comprehensively considering the monitoring temperature values collected by multiple temperature monitoring modules and combining the thermal characteristics and power consumption of the power semiconductor, and is used to measure the temperature of the internal heating point of the power semiconductor chip. The thermal characteristic parameter R θjc is the thermal resistance of the power semiconductor from the junction (chip) to the shell, and the power consumption p is the part of the electrical energy consumed by the power semiconductor in the working process converted into heat energy, which causes the internal temperature of the power semiconductor to rise. The thermal characteristic parameter R θjc and the power consumption p are both key parameters for calculating the temperature rise of the power semiconductor junction to the shell. In general, the thermal characteristic parameter R θjc can be obtained from the data manual of the power semiconductor. At the same time, in order to more accurately obtain the power consumption p, high-precision current and voltage sensors can be used to measure the working current and working voltage of the power semiconductor in real time, and the power consumption p is the product of the working current and the working voltage. The monitoring temperature value, the thermal characteristic parameter and the power consumption are all necessary parameters for calculating the comprehensive monitoring temperature value, the difference is that the monitoring temperature value provides the temperature condition of the power semiconductor shell, while the thermal characteristic parameter and the power consumption are used to calculate the temperature rise of the power semiconductor junction to the shell, i.e. the temperature higher than the shell. The weight of the monitoring temperature value is the importance of the temperature monitoring module corresponding to each monitoring temperature value in all temperature monitoring modules, which can be set according to the contribution of the temperature monitoring module in the monitoring process. In general, modern power semiconductor modules (such as automotive IGBT) usually reserve shell temperature measurement points to facilitate the installation of sensors for temperature acquisition. The present application uses the monitoring temperature value to provide the external temperature of the power semiconductor, uses the thermal characteristic parameter and the power consumption to calculate the internal junction temperature of the power semiconductor, and improves the temperature monitoring accuracy by comprehensively considering the external temperature and the internal junction temperature of the power semiconductor.

[0187] S7, based on the comprehensive monitoring temperature value and the temperature change rate set, confirming the secondary monitoring state of the power semiconductor, realizing the fault warning of the power semiconductor, wherein the secondary monitoring state is a secondary warning state or other secondary state.

[0188] It should be explained that the power semiconductor secondary monitoring state is confirmed based on the comprehensive monitoring temperature value and the temperature change rate set, including:

[0189] The following operations are performed on each temperature change rate in the temperature change rate set:

[0190] An absolute temperature change rate is obtained based on the temperature change rate, wherein the absolute temperature change rate is an absolute value of the temperature change rate;

[0191] The absolute temperature change rate is compared with a preset temperature change rate threshold value;

[0192] If the absolute temperature change rate is greater than the temperature change rate threshold value, the absolute temperature change rate is an unqualified absolute temperature change rate, otherwise, the absolute temperature change rate is a qualified absolute temperature change rate;

[0193] The unqualified absolute temperature change rates and the qualified absolute temperature change rates are respectively summarized to obtain an unqualified absolute temperature change rate set and a qualified absolute temperature change rate set;

[0194] The number of unqualified absolute temperature change rates in the unqualified absolute temperature change rate set and the number of qualified absolute temperature change rates in the qualified absolute temperature change rate set are respectively counted to obtain an unqualified number and a qualified number;

[0195] It is judged whether the comprehensive monitoring temperature value, the unqualified number and the qualified number satisfy a preset third verification condition, wherein the third verification condition is as follows:

[0196] |T b -T′|>∈,

[0197] Wherein, T' represents a preset comprehensive temperature reference value, ∈ represents a preset comprehensive temperature difference threshold value, Q1 represents the unqualified number, Q2 represents the qualified number, and σ represents a preset monitoring ratio;

[0198] When the third verification condition is established, the power semiconductor secondary monitoring state is confirmed as a secondary early warning state;

[0199] Otherwise, the power semiconductor secondary monitoring state is confirmed as other secondary states.

[0200] It can be understood that the secondary monitoring state refers to a monitoring state determined by further evaluating the state of the power semiconductor based on the comprehensive monitoring temperature value and the temperature rate set after confirming that the primary monitoring state is the primary early warning state. The difference from the primary monitoring state is that the secondary monitoring state confirms the state of the power semiconductor by evaluating the thermal state of the power semiconductor, while the primary monitoring state confirms the state of the power semiconductor by judging whether the electrical parameters and frequency parameters of the power semiconductor are abnormal. The secondary early warning state refers to a state of the power semiconductor when the comprehensive monitoring temperature value and the temperature rate both exceed the safe range but have not reached the failure range during the secondary detection, and the other secondary states indicate other states of the power semiconductor in addition to the secondary early warning state during the secondary monitoring.

[0201] It should be understood that the temperature rate threshold is a reference value artificially set for evaluating the temperature rate. For example, assuming that the temperature monitoring module collects temperature every 1 minute during the monitoring period, and the corresponding temperature rate set obtained by 5 temperature monitoring modules is {-0.45, -0.51, -0.49, -0.46, -0.53}, and only -0.45 is taken as an example: -0.45 indicates that the temperature decreases by 0.45°C per minute, -0.51, -0.49, -0.46, and -0.53 can achieve the same effect as -0.45, and will not be described here. The absolute temperature rate represents the absolute value of the temperature rate, and based on the temperature rate set {-0.45, -0.51, -0.49, -0.46, -0.53}, the absolute temperature rate corresponding to each temperature rate is 0.45, 0.51, 0.49, 0.46, and 0.53, respectively. Assuming that the temperature rate threshold is 0.50, the temperature rate corresponding to the absolute temperature rate greater than the temperature rate threshold 0.50 is taken as the unqualified absolute temperature rate, and otherwise, the temperature rate is taken as the qualified absolute temperature rate. From the example, the unqualified absolute temperature rate is 0.51 and 0.53, and the qualified absolute temperature rate is 0.45, 0.49, and 0.46. Therefore, the unqualified number Q1 is 2 and the qualified number Q2 is 3. The comprehensive temperature reference value and the comprehensive temperature difference threshold are used to evaluate the working temperature of the power semiconductor, which can be set according to the data manual of the power semiconductor. When the difference between the comprehensive temperature monitoring value and the comprehensive temperature reference value exceeds the comprehensive temperature difference threshold and When the second verification condition is established when the difference between the comprehensive temperature monitoring value and the comprehensive temperature reference value is greater than the monitoring ratio, it indicates that the secondary monitoring state of the power semiconductor is the secondary early warning state, and the power semiconductor needs to be confirmed. The present application evaluates the thermal state of the power semiconductor based on the comprehensive monitoring temperature value and the temperature rate set, accurately judges whether the power semiconductor is in the secondary early warning state through the second verification condition, can timely find potential failure, and improves the reliability and safety of the operation of the power semiconductor.

[0202] The application receives a failure warning instruction of a power semiconductor, confirms a failure warning system based on the failure warning instruction, wherein the failure warning system comprises an electrical parameter monitoring unit, a frequency monitoring unit and a temperature monitoring unit, the frequency monitoring unit comprises a low-frequency monitoring module and a high-frequency monitoring module, an electrical evaluation node is obtained based on the power semiconductor, the electrical evaluation node comprises a standard voltage, a standard current, a voltage warning deviation value interval and a current warning deviation value interval, and the electrical parameter allowed deviation value and the electrical parameter failure deviation value are respectively taken as the minimum value and the maximum value of the electrical parameter warning deviation value interval, the range between the allowed deviation and the failure deviation is taken as the warning range, the power semiconductor can be adjusted in time to ensure its stable operation when the deviation of the monitored electrical parameter value exceeds the allowed range but has not reached the failure deviation value, an electrical parameter node set is obtained based on a preset electrical monitoring period, a preset electrical monitoring time interval and the electrical parameter monitoring unit, the electrical parameter node set comprises a plurality of electrical parameter nodes, each electrical parameter node comprises a monitoring voltage and a monitoring current, a frequency evaluation ratio is obtained by using the low-frequency monitoring module and the high-frequency monitoring module, a first-level monitoring state of the power semiconductor is confirmed based on the electrical parameter node set, the frequency evaluation ratio and the electrical evaluation node, the first-level monitoring state is a first-level warning state or other first-level state, the low-frequency monitoring module (steady-state analysis) and the high-frequency monitoring module (transient-state analysis) are alternately sampled in time sequence, the steady-state frequency average and the transient-state frequency burst value are comprehensively considered, the blind area missed detection limitation caused by the fixed duty cycle phase in the traditional single sampling mode is broken through, the warning reliability and accuracy are improved, the dynamic weight method is used to obtain the weights of the three indexes used for calculating the first evaluation value, the related weight of the voltage fluctuation frequency index is dynamically increased when the voltage proportion corresponding to the voltage fluctuation is larger, the key index influence is highlighted, and the potential failure risk is captured in time, after the first-level monitoring state is confirmed as the first-level warning state, a temperature monitoring module set is obtained based on the temperature monitoring unit, a monitoring temperature set and a temperature change rate set are obtained by using the temperature monitoring module set, the temperature monitoring module set comprises a plurality of temperature monitoring modules, the monitoring temperature set comprises a plurality of monitoring temperature values, and the temperature monitoring module and the monitoring temperature value are in one-to-one correspondence, the initial abnormal temperature value is identified and removed by using the monitoring temperature value obtaining scheme, the calculated monitoring temperature value is closer to the true situation, the accuracy and reliability of temperature monitoring are improved, the external temperature of the power semiconductor is provided by using the monitoring temperature value, the internal node temperature of the power semiconductor is calculated by using the thermal characteristic parameter and the power consumption, the temperature monitoring accuracy is improved by comprehensively considering the external temperature and the internal node temperature of the power semiconductor, a comprehensive monitoring temperature value is obtained based on the monitoring temperature set and a pre-constructed temperature calculation formula, a second-level monitoring state of the power semiconductor is confirmed based on the comprehensive monitoring temperature value and the temperature change rate set, and the failure warning of the power semiconductor is realized.The secondary monitoring state is a secondary early warning state or other secondary state, and the heat state of the power semiconductor is evaluated based on the comprehensive monitoring temperature value and temperature change rate set, and the second verification condition is used to accurately determine whether the power semiconductor is in the secondary early warning state, so that potential faults can be found in time, and the reliability and safety of the power semiconductor operation are improved.

[0203] As Figure 2 shown is a functional module diagram of the data-driven power semiconductor fault early warning system provided by an embodiment of the application.

[0204] The data-driven power semiconductor fault early warning system 100 can be installed in an electronic device. According to the functions to be implemented, the data-driven power semiconductor fault early warning system 100 can include an electrical parameter acquisition module 101, a primary monitoring early warning module 102, a comprehensive temperature acquisition module 103, and a secondary monitoring early warning module 104. The modules of the application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0205] The electrical parameter acquisition module 101 is configured to receive a fault early warning instruction of the power semiconductor, and confirm a fault early warning system based on the fault early warning instruction, wherein the fault early warning system includes an electrical parameter monitoring unit, a frequency monitoring unit, and a temperature monitoring unit, wherein the frequency monitoring unit includes a low-frequency monitoring module and a high-frequency monitoring module.

[0206] An electrical evaluation node is acquired based on the power semiconductor, wherein the electrical evaluation node includes a standard voltage, a standard current, a voltage early warning deviation value interval, and a current early warning deviation value interval.

[0207] An electrical parameter node set is acquired based on a preset electrical monitoring time period, a preset electrical monitoring time interval, and the electrical parameter monitoring unit, wherein the electrical parameter node set includes a plurality of electrical parameter nodes, and each electrical parameter node includes a monitoring voltage and a monitoring current.

[0208] The primary monitoring early warning module 102 is configured to acquire a frequency evaluation ratio using the low-frequency monitoring module and the high-frequency monitoring module, and confirm a primary monitoring state of the power semiconductor based on the electrical parameter node set, the frequency evaluation ratio, and the electrical evaluation node, wherein the primary monitoring state is a primary early warning state or other primary state.

[0209] The comprehensive temperature acquisition module 103 is configured to, after confirming that the first-level monitoring state is a first-level early warning state, acquire a temperature monitoring module set based on the temperature monitoring unit, acquire a monitoring temperature set and a temperature change rate set by using the temperature monitoring module set, wherein the temperature monitoring module set comprises a plurality of temperature monitoring modules, the monitoring temperature set comprises a plurality of monitoring temperature values, and the temperature monitoring modules and the monitoring temperature values are in one-to-one correspondence.

[0210] The comprehensive monitoring temperature value is acquired based on the monitoring temperature set and a pre-constructed temperature calculation formula.

[0211] The second-level monitoring early warning module 104 is configured to confirm a second-level monitoring state of the power semiconductor based on the comprehensive monitoring temperature value and the temperature change rate set, and realize early warning of a fault of the power semiconductor, wherein the second-level monitoring state is a second-level early warning state or another second-level state.

[0212] In detail, the modules in the data-driven power semiconductor fault early warning system 100 in the embodiment of the present application adopt the same technical means as the data-driven power semiconductor fault early warning method in the above Figure 1 , and can produce the same technical effects, which will not be described here.

[0213] As shown in Figure 3 , it is a structural schematic diagram of an electronic device for implementing the data-driven power semiconductor fault early warning method according to an embodiment of the present application.

[0214] The electronic device 1 can include a processor 10, a memory 11 and a bus 12, and can further include a computer program stored in the memory 11 and executable on the processor 10, such as a data-driven power semiconductor fault early warning method program.

[0215] The memory 11 includes at least one type of readable storage medium, such as a flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., an SD or DX memory, etc.), a magnetic memory, a disk, an optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 11 includes both an internal storage unit and an external storage device of the electronic device 1. The memory 11 can be used to store application software and various data installed in the electronic device 1, such as the code of the data-driven power semiconductor fault warning method program, and can also be used to temporarily store data that has been output or will be output.

[0216] The processor 10 can be composed of an integrated circuit in some embodiments, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more combinations of a central processing unit (CPU), a microprocessor, a digital processing chip, a graphics processor, and various control chips, etc. The processor 10 is the control unit of the electronic device, which connects various components of the entire electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (such as the data-driven power semiconductor fault warning method program, etc.), and calls data stored in the memory 11 to perform various functions and process data of the electronic device 1.

[0217] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0218] Figure 3 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 3The illustrated structure does not constitute a limitation on the electronic device 1, and can include fewer or more components than illustrated, or combine certain components, or different component arrangements.

[0219] For example, although not shown, the electronic device 1 can also include a power source (such as a battery) to power the various components. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so that functions such as charge management, discharge management, and power consumption management can be achieved through the power management device. The power source can also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components. The electronic device 1 can also include various sensors, Bluetooth modules, Wi-Fi modules, and the like, which are not described here.

[0220] Further, the electronic device 1 can also include a network interface, which can optionally include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is typically used to establish a communication connection between the electronic device 1 and other electronic devices.

[0221] Optionally, the electronic device 1 can also include a user interface, which can be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch, etc. The display can also be appropriately referred to as a display screen or a display unit, and is used to display information processed in the electronic device 1 and to display a visualized user interface.

[0222] The data-driven power semiconductor fault warning method program stored in the memory 11 in the electronic device 1 is a combination of multiple instructions, which, when executed in the processor 10, can achieve:

[0223] Receiving a fault warning instruction of a power semiconductor, and confirming a fault warning system based on the fault warning instruction, wherein the fault warning system includes an electrical parameter monitoring unit, a frequency monitoring unit, and a temperature monitoring unit, wherein the frequency monitoring unit includes a low frequency monitoring module and a high frequency monitoring module;

[0224] Obtaining an electrical evaluation node based on the power semiconductor, wherein the electrical evaluation node includes a standard voltage, a standard current, a voltage warning deviation value interval, and a current warning deviation value interval;

[0225] obtaining the electrical parameter node set based on the preset electrical monitoring period, the preset electrical monitoring time interval and the electrical parameter monitoring unit, wherein the electrical parameter node set comprises a plurality of electrical parameter nodes, and each electrical parameter node comprises a monitored voltage and a monitored current;

[0226] obtaining the frequency evaluation ratio by using the low-frequency monitoring module and the high-frequency monitoring module, and confirming the first monitoring state of the power semiconductor based on the electrical parameter node set, the frequency evaluation ratio and the electrical evaluation node, wherein the first monitoring state is a first early warning state or other first state;

[0227] when the first monitoring state is confirmed as the first early warning state, obtaining the temperature monitoring module set based on the temperature monitoring unit, and obtaining the monitored temperature set and the temperature change rate set by using the temperature monitoring module set, wherein the temperature monitoring module set comprises a plurality of temperature monitoring modules, the monitored temperature set comprises a plurality of monitored temperature values, and the temperature monitoring module and the monitored temperature value are in one-to-one correspondence;

[0228] obtaining the comprehensive monitored temperature value based on the monitored temperature set and the pre-constructed temperature calculation formula;

[0229] confirming the second monitoring state of the power semiconductor based on the comprehensive monitored temperature value and the temperature change rate set, and realizing the fault early warning of the power semiconductor, wherein the second monitoring state is a second early warning state or other second state.

[0230] Specifically, the specific implementation method of the processor 10 to the above instructions can refer to Figures 1 to 3 The description of related steps in the corresponding embodiments will not be repeated here.

[0231] Further, the modules / units integrated in the electronic device 1 are implemented in the form of software function units and sold or used as independent products, which can be stored in a computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM).

[0232] The application also provides a computer readable storage medium, which stores a computer program, and the computer program can realize the following when executed by a processor of an electronic device:

[0233] Receive a failure warning instruction of the power semiconductor, and confirm a failure warning system based on the failure warning instruction, wherein the failure warning system comprises an electrical parameter monitoring unit, a frequency monitoring unit and a temperature monitoring unit, and the frequency monitoring unit comprises a low-frequency monitoring module and a high-frequency monitoring module.

[0234] Obtain an electrical evaluation node based on the power semiconductor, wherein the electrical evaluation node comprises a standard voltage, a standard current, a voltage warning deviation value interval and a current warning deviation value interval.

[0235] Obtain an electrical parameter node set based on a preset electrical monitoring time period, a preset electrical monitoring time interval and the electrical parameter monitoring unit, wherein the electrical parameter node set comprises a plurality of electrical parameter nodes, and each electrical parameter node comprises a monitoring voltage and a monitoring current.

[0236] Obtain a frequency evaluation ratio by using the low-frequency monitoring module and the high-frequency monitoring module, and confirm a first monitoring state of the power semiconductor based on the electrical parameter node set, the frequency evaluation ratio and the electrical evaluation node, wherein the first monitoring state is a first warning state or another first state.

[0237] When the first monitoring state is confirmed as the first warning state, obtain a temperature monitoring module set based on the temperature monitoring unit, and obtain a monitoring temperature set and a temperature change rate set by using the temperature monitoring module set, wherein the temperature monitoring module set comprises a plurality of temperature monitoring modules, the monitoring temperature set comprises a plurality of monitoring temperature values, and the temperature monitoring modules and the monitoring temperature values are in one-to-one correspondence.

[0238] Obtain a comprehensive monitoring temperature value based on the monitoring temperature set and a pre-constructed temperature calculation formula.

[0239] Confirm a second monitoring state of the power semiconductor based on the comprehensive monitoring temperature value and the temperature change rate set, and realize failure warning of the power semiconductor, wherein the second monitoring state is a second warning state or another second state.

[0240] In several embodiments provided in the present application, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the above-described system embodiments are only illustrative, and actual implementation can have another division way.

[0241] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs.

[0242] In addition, each function module in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software function module.

[0243] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be realized in other specific forms without departing from the spirit or essential characteristics of the present application.

[0244] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A data-driven power semiconductor fault early warning method, characterized in that: The method comprises: Receiving a fault warning instruction of a power semiconductor, and confirming a fault warning system based on the fault warning instruction, wherein the fault warning system includes: an electrical parameter monitoring unit, a frequency monitoring unit and a temperature monitoring unit, wherein the frequency monitoring unit includes: a low frequency monitoring module and a high frequency monitoring module; Obtaining an electrical evaluation node based on a power semiconductor, wherein the electrical evaluation node includes a standard voltage, a standard current, a voltage warning deviation value interval, and a current warning deviation value interval; Acquire an electrical parameter node set based on a preset electrical monitoring period, a preset electrical monitoring time interval, and the electrical parameter monitoring unit, wherein the electrical parameter node set includes a plurality of electrical parameter nodes, and each electrical parameter node includes a monitoring voltage and a monitoring current; Obtaining a frequency assessment ratio using a low-frequency monitoring module and a high-frequency monitoring module, and confirming a primary monitoring state of the power semiconductor based on the electrical parameter node set, the frequency assessment ratio, and the electrical assessment node, wherein the primary monitoring state is a primary warning state or other primary state; When the first-level monitoring state is confirmed to be the first-level warning state, a temperature monitoring module set is obtained based on the temperature monitoring unit, and a monitoring temperature set and a temperature change rate set are obtained using the temperature monitoring module set, wherein the temperature monitoring module set includes multiple temperature monitoring modules, the monitoring temperature set includes multiple monitoring temperature values, and the temperature monitoring modules correspond to the monitoring temperature values ​​one by one; Obtain comprehensive monitoring temperature values ​​based on the monitoring temperature set and pre-built temperature calculation formula; The secondary monitoring state of the power semiconductor is confirmed based on the comprehensive monitoring temperature value and the temperature change rate set to realize the fault warning of the power semiconductor, wherein the secondary monitoring state is a secondary warning state or other secondary states.

2. The data-driven power semiconductor fault early warning method according to claim 1, characterized in that: The obtaining of an electrical evaluation node based on a power semiconductor comprises: Obtain standard voltage and standard current of power semiconductors; Obtaining the voltage tolerance and voltage fault tolerance of power semiconductors; Obtaining a voltage warning deviation value interval based on the voltage allowable deviation value and the voltage fault deviation value, wherein the minimum value and maximum value corresponding to the voltage warning deviation value interval are the voltage allowable deviation value and the voltage fault deviation value, respectively; Obtaining the current allowable deviation value and current fault deviation value of the power semiconductor; Obtaining a current warning deviation value interval based on the current allowable deviation value and the current fault deviation value, wherein the minimum value and the maximum value corresponding to the current warning deviation value interval are the current allowable deviation value and the current fault deviation value, respectively; The standard voltage, standard current, voltage warning deviation value interval and current warning deviation value interval are associated to obtain an electrical evaluation node.

3. The data-driven power semiconductor fault early warning method according to claim 2, characterized in that: The method of obtaining the frequency assessment ratio by using the low-frequency monitoring module and the high-frequency monitoring module includes: Obtain a frequency monitoring period, and obtain multiple frequency monitoring sub-periods based on the frequency monitoring period; Sorting the multiple frequency monitoring sub-periods according to the order of time corresponding to the frequency monitoring sub-periods from front to back to obtain a frequency monitoring sub-period sequence; Acquire multiple odd frequency monitoring sub-periods and multiple even frequency monitoring sub-periods based on the frequency monitoring sub-period sequence, wherein the odd frequency monitoring sub-period is a frequency monitoring sub-period with an odd sequence in the frequency monitoring sub-period sequence, and the even frequency monitoring sub-period is a frequency monitoring sub-period with an even sequence in the frequency monitoring sub-period sequence; Acquire a first frequency value set based on a plurality of odd-frequency monitoring sub-periods, a preset first monitoring number, and a low-frequency monitoring module; Summarizing the first frequency value sets to obtain multiple first frequency value sets; Obtaining a second frequency value set based on a plurality of even frequency monitoring sub-periods, a preset second monitoring number, and a high frequency monitoring module; Summarizing the second frequency value sets to obtain multiple second frequency value sets; A frequency evaluation ratio is obtained based on the plurality of first frequency value sets, the plurality of second frequency value sets, and a preset method.

4. The data-driven power semiconductor fault early warning method according to claim 3, characterized in that: The method of confirming the primary monitoring status of the power semiconductor based on the electrical parameter node set, the frequency evaluation ratio, and the electrical evaluation node includes: Sort the electrical parameter nodes in the electrical parameter node set according to the time corresponding to the electrical parameter nodes from front to back to obtain an electrical parameter node sequence; Extracting electrical parameter nodes sequentially from the electrical parameter node sequence, and identifying a reference electrical parameter node in the electrical parameter node sequence based on the extracted electrical parameter nodes, wherein the reference electrical parameter node is adjacent to the extracted electrical parameter node and lags behind the extracted electrical parameter node; Calculating an absolute difference between a monitored voltage in an electrical parameter node and a monitored voltage in a reference electrical parameter node, and taking the absolute difference as a voltage fluctuation difference; comparing the voltage fluctuation difference with a preset voltage fluctuation threshold; If the voltage fluctuation difference is greater than the voltage fluctuation threshold, confirming the monitored voltage corresponding to the reference electrical parameter node as a fluctuating voltage; Summarizing the fluctuating voltages to obtain a fluctuating voltage set, and counting the number of fluctuating voltages in the fluctuating voltage set to obtain a fluctuating voltage quantity; Counting the number of electrical parameter nodes in the electrical parameter node sequence to obtain the total number of electrical parameter nodes; Obtaining a weight node based on the number of fluctuating voltages, the total number of electrical parameter nodes, and a preset initial weight node, wherein the initial weight node includes: an initial first weight, an initial second weight, and an initial third weight, and the weight node includes: a first weight, a second weight, and a third weight; Obtaining a first evaluation value based on an electrical parameter node sequence, a fluctuating voltage quantity, an electrical evaluation node, a weight node, and a pre-established evaluation value calculation formula; Obtaining a second evaluation value based on the electrical parameter node set and the electrical evaluation node; respectively comparing the first evaluation value with a preset first warning threshold, the second evaluation value with a preset second warning threshold, and the frequency evaluation ratio with a preset frequency evaluation ratio threshold; If the first evaluation value is greater than the first warning threshold, or the second evaluation value is greater than the second warning threshold, or the frequency evaluation ratio is greater than the frequency evaluation ratio threshold, confirming the first-level monitoring state of the power semiconductor as a first-level warning state; Otherwise, the primary monitoring state of the power semiconductor is confirmed as other primary states.

5. The data-driven power semiconductor fault early warning method according to claim 4, characterized in that: The obtaining of weight nodes based on the number of fluctuating voltages, the total number of electrical parameter nodes, and preset initial weight nodes includes: Calculate the ratio of the number of fluctuating voltages to the total number of electrical parameter nodes to obtain the voltage ratio; comparing the voltage ratio with a preset ratio threshold; If the voltage ratio is less than or equal to the ratio threshold, the initial weight node is used as the weight node; otherwise, an updated first weight, an updated second weight, and an updated third weight are obtained based on the number of fluctuating voltages, the total number of electrical parameter nodes, and a pre-established updated weight calculation formula; Compare and update the first weight with the minimum weight; If the updated first weight is greater than or equal to the minimum weight, the updated first weight, the updated second weight, and the updated third weight are used as the first weight, the second weight, and the third weight respectively; otherwise, the minimum weight is used as the updated first weight, and the first weight, the second weight, the updated third weight, and the preset normalization method are used to obtain the first weight, the second weight, and the third weight; The first weight, the second weight, and the third weight are summed up to obtain a weight node.

6. The data-driven power semiconductor fault early warning method according to claim 5, characterized in that: The method of obtaining a monitoring temperature set and a temperature change rate set by using a temperature monitoring module set includes: For each temperature monitoring module in the temperature monitoring module set, perform the following operations: Obtaining an initial monitoring temperature set using a temperature monitoring module, a preset temperature monitoring period, and a preset temperature monitoring number, wherein the initial monitoring temperature set includes a plurality of initial monitoring temperature values; Summarize the initial monitoring temperature sets to obtain multiple initial monitoring temperature sets, and the initial monitoring temperature sets correspond one-to-one to the temperature monitoring modules; The following operations are performed on each of the multiple initial monitoring temperature sets: A monitoring temperature value acquisition scheme is constructed based on the initial monitoring temperature set, wherein the monitoring temperature value acquisition scheme is as follows: Among them, T avg Indicates the monitored temperature value, T i represents the i-th initial monitoring temperature value in the initial monitoring temperature set, T ak represents the preset kth initial temperature anomaly value, α represents the preset temperature threshold, n represents the total number of n initial monitoring temperature values ​​in the initial monitoring temperature set, and m represents the total number of m preset initial temperature anomaly values; Acquire a monitoring temperature value based on a monitoring temperature value acquisition scheme; After confirming that each temperature monitoring module has obtained the corresponding monitoring temperature value, the monitoring temperature values ​​are summarized to obtain a monitoring temperature set; A temperature change rate set is obtained based on a plurality of initial monitored temperature sets.

7. The data-driven power semiconductor fault early warning method according to claim 6, characterized in that: The step of obtaining a temperature change rate set based on a plurality of initial monitored temperature sets includes: The following steps are performed for each of the multiple initial monitoring temperature sets: Sorting the initial monitoring temperature values ​​in the initial monitoring temperature set in order from front to back of the time corresponding to the acquisition of the initial monitoring temperature values ​​to obtain an initial monitoring temperature sequence; Obtaining the temperature change rate based on the initial monitored temperature sequence and a pre-established temperature change rate calculation formula; The temperature change rates are summarized to obtain a temperature change rate set.

8. The data-driven power semiconductor fault early warning method according to claim 7, characterized in that: The temperature calculation formula is as follows: Among them, T b represents the comprehensive monitoring temperature value, l represents the monitoring temperature set has l monitoring temperature values, T j-avg represents the jth monitored temperature value in the monitored temperature set, w j Represents the weight of the jth monitored temperature value, R θjc It represents the thermal resistance from the power semiconductor chip to the casing, and p represents the power consumption of the power semiconductor.

9. The data-driven power semiconductor fault early warning method according to claim 8, characterized in that: The method of confirming the secondary monitoring status of the power semiconductor based on the comprehensive monitoring temperature value and temperature change rate set includes: The following operations are performed on each temperature change rate in the temperature change rate set: Obtaining an absolute temperature change rate based on the temperature change rate, wherein the absolute temperature change rate is an absolute value of the temperature change rate; comparing the absolute temperature change rate with a preset temperature change rate threshold; If the absolute temperature change rate is greater than the temperature change rate threshold, the absolute temperature change rate is regarded as an unqualified absolute temperature change rate; otherwise, the absolute temperature change rate is regarded as a qualified absolute temperature change rate; Summarize the unqualified absolute temperature change rates and the qualified absolute temperature change rates respectively to obtain an unqualified absolute temperature change rate set and a qualified absolute temperature change rate set; Counting the number of unqualified absolute temperature change rates in the unqualified absolute temperature change rate set and the number of qualified absolute temperature change rates in the qualified absolute temperature change rate set, respectively, to obtain the number of unqualified and qualified; Determine whether the comprehensive monitoring temperature value, the number of unqualified items, and the number of qualified items meet the preset third verification condition; When the third verification condition is met, the secondary monitoring state of the power semiconductor is confirmed as the secondary warning state; Otherwise, the secondary monitoring state of the power semiconductor is confirmed as other secondary states.

10. A data-driven power semiconductor fault warning system, characterized in that: The system comprises: An electrical parameter acquisition module is used to receive a fault warning instruction of a power semiconductor and confirm a fault warning system based on the fault warning instruction, wherein the fault warning system includes: an electrical parameter monitoring unit, a frequency monitoring unit and a temperature monitoring unit, wherein the frequency monitoring unit includes: a low-frequency monitoring module and a high-frequency monitoring module; Obtaining an electrical evaluation node based on a power semiconductor, wherein the electrical evaluation node includes a standard voltage, a standard current, a voltage warning deviation value interval, and a current warning deviation value interval; Acquire an electrical parameter node set based on a preset electrical monitoring period, a preset electrical monitoring time interval, and the electrical parameter monitoring unit, wherein the electrical parameter node set includes a plurality of electrical parameter nodes, and each electrical parameter node includes a monitoring voltage and a monitoring current; A first-level monitoring and early warning module, configured to obtain a frequency assessment ratio using a low-frequency monitoring module and a high-frequency monitoring module, and to determine a first-level monitoring state of the power semiconductor based on the electrical parameter node set, the frequency assessment ratio, and the electrical assessment node, wherein the first-level monitoring state is a first-level early warning state or other first-level state; The integrated temperature acquisition module is used to obtain a temperature monitoring module set based on the temperature monitoring unit after confirming that the first-level monitoring state is the first-level warning state, and to obtain a monitoring temperature set and a temperature change rate set using the temperature monitoring module set, wherein the temperature monitoring module set includes multiple temperature monitoring modules, the monitoring temperature set includes multiple monitoring temperature values, and the temperature monitoring modules correspond to the monitoring temperature values ​​one by one; Obtain comprehensive monitoring temperature values ​​based on the monitoring temperature set and pre-built temperature calculation formula; The secondary monitoring and early warning module is used to confirm the secondary monitoring status of the power semiconductor based on the comprehensive monitoring temperature value and temperature change rate set, and realize the fault early warning of the power semiconductor, wherein the secondary monitoring status is the secondary early warning status or other secondary status.

Images