Electrical fire early warning system and method based on multi-sensor fusion

Abstract

The present invention relates to the technical field of safety monitoring and early warning, and specifically to an electrical fire early warning system and method based on multi-sensor fusion, wherein the system comprises a plurality of sensors: for real-time monitoring of the working status and environmental parameters of electrical equipment; a data acquisition module: for collecting data of each sensor and performing preliminary data processing; a data fusion processing unit: for adopting a data fusion algorithm to comprehensively analyze the data of each sensor and identify potential fire risks; an early warning decision module: for judging whether there is a fire risk and deciding whether to issue an early warning signal according to the analysis result of the data fusion processing unit; a communication interface: for realizing remote monitoring and data transmission functions and supporting linkage with other safety systems; a user interface: for providing users with an intuitive operation interface and early warning information display; the present application can more accurately assess the risk of electrical fires, effectively reduce the false alarm rate, and improve the timeliness of early warnings.

Description

Technical Field

[0001] The present invention relates to the technical field of safety monitoring and early warning, and in particular to an electrical fire early warning system and method based on multi-sensor fusion. Background Art

[0002] Traditional electrical fire warning systems often rely on a single type of sensor, such as smoke sensors or temperature sensors. This single monitoring method has problems such as high false alarm rate and untimely warning.

[0003] The publication number CN110942586A discloses a visual electrical fire intelligent early warning system, which includes an early warning body, a microprocessor, and an electrical detection module, a fire detection module, and a communication module connected to the microprocessor through a data line. The electrical detection module includes a residual current detection module, a current detection module, and a voltage detection module; the fire detection module includes a smoke sensor, a toxic gas sensor, an external temperature sensor, and a camera; although multiple sensors are involved to monitor the fire situation at all times and effectively prevent the fire from causing huge losses to human life and property, there are still problems such as low early warning accuracy and insufficient response time. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide an electrical fire warning system and method based on multi-sensor fusion.

[0005] The technical solution adopted by the present invention to solve the technical problem is: an electrical fire warning system based on multi-sensor fusion includes:

[0006] Various sensors: used to monitor the working status and environmental parameters of electrical equipment in real time;

[0007] Data acquisition module: used to collect data from each sensor and perform preliminary data processing;

[0008] Data fusion processing unit: uses data fusion algorithm to comprehensively analyze the data of each sensor and identify potential fire risks;

[0009] Early warning decision module: Based on the analysis results of the data fusion processing unit, it determines whether there is a fire risk and decides whether to issue an early warning signal;

[0010] Communication interface: realize remote monitoring and data transmission functions, and support linkage with other security systems;

[0011] User interface: Provide users with an intuitive operation interface and warning information display.

[0012] The sensors include a smoke sensor, a temperature sensor, a current sensor and a voltage sensor.

[0013] The electrical fire early warning method based on multi-sensor fusion is applied to the above-mentioned electrical fire early warning system based on multi-sensor fusion, and includes the following steps:

[0014] S1: Obtain the target area identifier of the area where the target substation is located;

[0015] S2: If the target area identifier identifies the area where the target substation is located as a main transformer area, proceed to step S3;

[0016] S3: Obtain the maximum ambient temperature identifier set E=(E1, E2, ..., Ea, ..., Eb) corresponding to the target main transformer protection cabinet TRA2 in the target substation in the first target time window, where a=1, 2, ..., b, b is the number of first time periods arranged continuously in the first target time window, Ea is the maximum ambient temperature identifier corresponding to TRA2 in the ath first time period, the end time of the first target time window is the current time, and the length of the first target time window is b*ΔT1, where ΔT1 is the length of each first time period;

[0017] S4: Obtain the main transformer protection cabinet working information set F=(F1, F2, ..., Fa, ..., Fb) corresponding to TRA2 in the first target time window, where Fa is the main transformer protection cabinet working information corresponding to TRA2 in the a-th first time period, Fa=(PFa, TFa, QFa), PFa is the maximum power consumption of TRA2 in the a-th first time period, TFa is the maximum operating temperature of TRA2 in the a-th first time period, and QFa is the weather type identifier corresponding to TRA2 in the a-th first time period;

[0018] S5: Get the basic information of the main transformer protection cabinet of TRA2 J = (Pmax, Pmin, L, S), where Pmax is the maximum output power of TRA2 in the first target time window, Pmin is the minimum output power of TRA2 in the first target time window, L is the number of households connected to TRA2, S is the service life of TRA2, and L meets the following conditions:

[0019] LZ<NUM1, then L=0;

[0020] NUM1≤LZ<NUM2, then L=1;

[0021] NUM2≤LZ<NUM3, then L=2;

[0022] NUM3≤LZ<NUM4, then L=3;

[0023] NUM4≤LZ, then L=4;

[0024] NUM1<NUM2<NUM3<NUM4;

[0025] Wherein, LZ is the number of households connected to TRA2; NUM1, NUM2, NUM3, NUM4 are the preset household number thresholds;

[0026] S6: Determine the target feature vector N=(E1, F1, E2, F2, …, Ea, Fa, …, Eb, Fb, Pmax, Pmin, L, S) corresponding to TRA2 based on E, F and J;

[0027] S7: Input N into the target AI model to obtain the predicted fire probability U corresponding to the target time length in the future output by TRA2 of the target AI model, where U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+m*Pmaβ+n*Pmin+v*L+w*S; wherein β1, β2,…,βa,…,βb, s1, s2,…,sa,…,sb, m, n, v, w are the parameters obtained by the target AI model after training. If U is greater than the preset probability threshold, a prompt message is output.

[0028] The step S3 includes the following sub-steps:

[0029] S3-1: Obtain the maximum ambient temperature set EZ=(EZ1, EZ2, ..., EZa, ..., EZb) corresponding to TRA2 in the first target time window, where EZa is the maximum ambient temperature corresponding to TRA2 in the ath first time period;

[0030] S3-2: Determine E according to EZ, where Ea is the temperature identifier corresponding to EZa;

[0031] Ea in S3-2 meets the following conditions:

[0032] EZa<TEMP1, then Ea=0;

[0033] TEMP1≤EZa<TEMP2, then Ea=1;

[0034] TEMP2≤EZa<TEMP3, then Ea=2;

[0035] TEMP3≤EZa<TEMP4, then Ea=3;

[0036] TEMP4≤EZa, then Ea=4;

[0037] TEMP1<TEMP2<TEMP3<TEMP4;

[0038] TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3;

[0039] Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

[0040] Before step S6, the method further includes the following steps:

[0041] S601: Obtain the estimated temperature set G=(G1, G2, ..., Gc, ..., Gd) corresponding to TRA2 in the first target time window; c=1, 2, ..., d; wherein Gc is the estimated maximum ambient temperature identifier of the cth day after the current time corresponding to TRA2; d is the estimated number of days after the current time;

[0042] Then step S6 comprises:

[0043] Determine the target feature vector N=(E1, F1, E2, F2, …, Ea, Fa, …, Eb, Fb, G1, G2, …, Gc, …, Gd, Pmax, Pmin, L, S) corresponding to TRA2 according to E, F, G and J;

[0044] U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+t1*G1+t2*G2+…+tc*Gc+…+td*Gd+m*Pmaβ+n*Pmin+v*L+w*S; among which, t1, t2,…, tc,…, td are the parameters obtained by the target AI model after training.

[0045] The method for obtaining the estimated temperature identification set G corresponding to TRA2 in the first target time window is as follows:

[0046] S601-1: Obtain the estimated ambient temperature set GZ=(GZ1, GZ2, ..., GZc, ..., GZd) corresponding to TRA2 in the first target time window; wherein GZc is the estimated maximum ambient temperature of TRA2 corresponding to the current time and the cth day after that;

[0047] S601-2: Determine G according to GZ, where Gc is the temperature identifier corresponding to GZc;

[0048] Gc meets the following criteria:

[0049] GZc<TEMP1, then Gc=0;

[0050] TEMP1≤GZc<TEMP2, then Gc=1;

[0051] TEMP2≤GZc<TEMP3, then Gc=2;

[0052] TEMP3≤GZc<TEMP4, then Gc=3;

[0053] TEMP4≤GZc, then Gc=4;

[0054] TEMP1<TEMP2<TEMP3<TEMP4;

[0055] TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3;

[0056] Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

[0057] Before step S6, the method further includes:

[0058] S602, obtaining a maintenance information set Y=(Y1, Y2, ..., Yg, ..., Yh) corresponding to TRA2 in the second target time window; g=1, 2, ..., h; h is the number of second time periods arranged continuously in the second target time window, Yg is the maintenance information corresponding to TRA2 in the g-th second time period Yg=(YJg, YGg), YJg is the number of inspections performed by TRA2 in the g-th second time period, YGg is the workpiece replacement information of the workpiece replaced by TRA2 in the g-th second time period, YGg=(YGg1, YGg2, ..., YGgθ, ..., YGgε), θ=1, 2, ... , ε; YGgθ is the workpiece replacement information of the θth workpiece replaced by TRA2 in the gth second time period, ε is the total number of workpieces replaced in TRA2, YGgθ=(YGTgθ, YGQgθ); YGTgθ is the replacement time of the θth workpiece replaced by TRA2 in the gth second time period; YGQgθ is the replacement reason identifier of the θth workpiece replaced by TRA2 in the gth second time period, the length of the second target time window is h*ΔT2, ΔT2 is the length of each second time period, (h*ΔT2)>(b*ΔT1), and ΔT2>ΔT1;

[0059] Then step S6 comprises:

[0060] According to E, F, G, J and Y, determine the target feature vector N = (E1, F1, E2, F2,…, Ea, Fa,…, Eb, Fb, G1, G2,…, Gc,…, Gd, Y1, Y2,…, Yg,…, Yh, Pmax, Pmin, L, S) corresponding to TRA2.

[0061] U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+π1*Y1+π2*Y2+…+πg*Yg+…+πh*Yh+m*Pmaβ+n*Pmin+v*L+w*S; π1, π2,…, πg,…, πh are the parameters obtained by the target AI model after training.

[0062] If the target area identifier in S2 identifies the area where the target substation is located as an industrial power consumption area, then proceed to step S8;

[0063] S8: Obtain the maximum ambient temperature identification set A=(A1, A2,…, Aa,…, Ab) corresponding to the target main transformer protection cabinet TRA1 in the target substation in the first target time window; a=1, 2,…, b; the target substation is located in the industrial power consumption area, b is the number of first time periods arranged continuously in the first target time window, Aa is the maximum ambient temperature identification corresponding to TRA1 in the ath first time period, and the end time of the first target time window is the current time.

[0064] The S8 comprises the following sub-steps:

[0065] S8-1: Obtain the maximum ambient temperature set AZ=(AZ1, AZ2, ..., AZa, ..., AZb) corresponding to TRA1 in the first target time window; wherein AZa is the maximum ambient temperature corresponding to TRA1 in the ath first time period;

[0066] S8-2: Determine A according to AZ, where Aa is the temperature identifier corresponding to AZa;

[0067] Aa meets the following conditions:

[0068] AZa<TEMP1, then Aa=0;

[0069] TEMP1≤AZa<TEMP2, then Aa=1;

[0070] TEMP2≤AZa<TEMP3, then Aa=2;

[0071] TEMP3≤AZa<TEMP4, then Aa=3;

[0072] TEMP4≤AZa, then Aa=4;

[0073] TEMP1<TEMP2<TEMP3<TEMP4;

[0074] TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3;

[0075] Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

[0076] The following steps are also included:

[0077] S9: Obtain a workpiece information set B=(B1, B2, ..., Ba, ..., Bb) corresponding to TRA1 in the first target time window, where a=1, 2, ..., b, and Ba is the workpiece information corresponding to TRA1 in the ath first time period;

[0078] S10: According to A and B, determine the target feature vector M=(A1, B1, A2, B2, …, Aa, Ba, …, Ab, Bb) corresponding to TRA1;

[0079] S11: According to A and B, determine the target feature vector M corresponding to TRA1, and input M into the target AI model to obtain the predicted probability V of occurrence of special circumstances corresponding to TRA1 output by the target AI model within the target time length in the future; V meets the following conditions: V=x1*A1+y1*B1+x2*A2+y2*B2+…+xa*Aa+ya*Ba+…+xb*Ab+yb*Bb; wherein x1, x2, …, xa, …, xb, y1, y2, …, ya, …, yb are the parameters of the target AI model obtained after training;

[0080] S12: If V is greater than a preset probability threshold, a prompt message is output.

[0081] Compared with the prior art, the present invention has the following beneficial effects:

[0082] The present invention can more accurately assess the risk of electrical fires, effectively reduce the false alarm rate, and improve the timeliness of early warnings through the fusion processing of multi-sensor data, thereby ensuring the safety of personnel and property.

[0083] For the target main transformer protection cabinet TRA2 in the target substation located in the main transformer cabinet area, the maximum ambient temperature identification set, the main transformer protection cabinet working information set and the main transformer protection cabinet basic information corresponding to the first target time window are obtained, and the maximum ambient temperature identification set, the main transformer protection cabinet working information set and the main transformer protection cabinet basic information corresponding to the first target time window are used as the target feature vector of TRA2. At the same time, the number and end time of the first time period of the time window are controlled, so that the parameters in the target feature vector can reflect the maximum ambient temperature changes, weather changes, output power changes of the target main transformer protection cabinet when it is working, workload changes, service life, maximum working temperature changes and other information of the target main transformer protection cabinet within a period of time shorter than the current time.

[0084] Since TRA2 is located in the main transformer cabinet area, and the main transformer cabinet area substation is characterized by high and low peaks in power usage, and the main transformer protection cabinet has rest time, so its output power and maximum operating temperature vary greatly. The output power of TRA2 during peak power consumption (daytime) is greater than the output power of TRA2 during low power consumption (nighttime), and the maximum operating temperature is the same. According to the maximum ambient temperature, weather type identifier, maximum / minimum output power and maximum operating temperature corresponding to each first time period in the first target time window, the heat dissipation of TRA2 can be determined as part of the TRA2 target feature vector, so that the final determined U is more accurate.

[0085] Basic information such as the number of households connected to TRA2, maximum power consumption, and service life are also important factors that cause TRA2 to spontaneously combust. The more households connected or the greater the maximum power consumption, the greater the current operating load of TRA2 and the greater the possibility of spontaneous combustion. The longer the service life, the more serious the aging of the internal workpieces of TRA2, and the greater the possibility of spontaneous combustion. Therefore, this application uses the above-mentioned maximum ambient temperature identification set, the main transformer protection panel cabinet working information set, and the main transformer protection panel cabinet basic information as the target feature vector of TRA2, so that the target AI model is more accurate when obtaining the predicted fire probability U. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0088] Example 1

[0089] An electrical fire warning system based on multi-sensor fusion, including

[0090] Various sensors: used to monitor the working status and environmental parameters of electrical equipment in real time; the sensors include but are not limited to smoke sensors, temperature sensors, current sensors and voltage sensors.

[0091] Data acquisition module: used to collect data from each sensor and perform preliminary data processing, such as filtering and A / D conversion;

[0092] Data fusion processing unit: uses advanced data fusion algorithms to conduct comprehensive analysis of data from various sensors to identify potential fire risks;

[0093] Early warning decision module: Based on the analysis results of the data fusion processing unit, it determines whether there is a fire risk and decides whether to issue an early warning signal;

[0094] Communication interface: realize the remote monitoring and data transmission functions of the system, and support linkage with other security systems;

[0095] User interface: Provide users with an intuitive operation interface and warning information display.

[0096] Example 2

[0097] Reference Figure 1 The electrical fire early warning method based on multi-sensor fusion is applied to the electrical fire early warning system based on multi-sensor fusion of Example 1, and comprises the following steps:

[0098] S1: Obtain the target area identifier of the area where the target substation is located;

[0099] S2: If the target area identifier identifies the area where the target substation is located as a main transformer area, proceed to step S3;

[0100] S3: Obtain the maximum ambient temperature identifier set E=(E1, E2, ..., Ea, ..., Eb) corresponding to the target main transformer protection cabinet TRA2 in the target substation in the first target time window, where a=1, 2, ..., b, b is the number of first time periods arranged continuously in the first target time window, Ea is the maximum ambient temperature identifier corresponding to TRA2 in the ath first time period, the end time of the first target time window is the current time, and the length of the first target time window is b*ΔT1, where ΔT1 is the length of each first time period;

[0101] The step S3 includes the following sub-steps:

[0102] S3-1: Obtain the maximum ambient temperature set EZ=(EZ1, EZ2, ..., EZa, ..., EZb) corresponding to TRA2 in the first target time window, where EZa is the maximum ambient temperature corresponding to TRA2 in the ath first time period;

[0103] S3-2: Determine E according to EZ, and further, Ea is the temperature identifier corresponding to EZa;

[0104] Ea meets the following conditions:

[0105] EZa<TEMP1, then Ea=0;

[0106] TEMP1≤EZa<TEMP2, then Ea=1;

[0107] TEMP2≤EZa<TEMP3, then Ea=2;

[0108] TEMP3≤EZa<TEMP4, then Ea=3;

[0109] TEMP4≤EZa, then Ea=4;

[0110] TEMP1<TEMP2<TEMP3<TEMP4;

[0111] TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3;

[0112] Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

[0113] In this embodiment, the maximum ambient temperature corresponding to all first time periods in the first target time window is divided into boxes through the above-mentioned multiple temperature intervals. Because at different temperatures, the same numerical change in temperature has different effects on the target main transformer protection cabinet. For example, when the temperature is below 90°C, it is the normal operating temperature range of the main transformer protection cabinet. Therefore, the change in temperature within this temperature range has basically no effect on the target main transformer protection cabinet. However, after the temperature reaches 105°C, the increase in temperature will have a greater impact on the main transformer protection cabinet. When the temperature rises to 120°C, the life of the main transformer protection cabinet is only 2 years. Therefore, in this embodiment, multiple temperature ranges of EZa are determined, and the corresponding final values ​​are different, and the length of the temperature interval will gradually decrease (i.e., TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3), so that the temperature mark can more accurately reflect the impact of its corresponding maximum ambient temperature on the target main transformer protection cabinet.

[0114] S4: Obtain the main transformer protection cabinet working information set F=(F1, F2, ..., Fa, ..., Fb) corresponding to TRA2 in the first target time window, where Fa is the main transformer protection cabinet working information corresponding to TRA2 in the a-th first time period, Fa=(PFa, TFa, QFa), PFa is the maximum power consumption of TRA2 in the a-th first time period, TFa is the maximum operating temperature of TRA2 in the a-th first time period, and QFa is the weather type identifier corresponding to TRA2 in the a-th first time period;

[0115] S5: Get the basic information of the main transformer protection cabinet of TRA2 J = (Pmax, Pmin, L, S), where Pmax is the maximum output power of TRA2 in the first target time window; Pmin is the minimum output power of TRA2 in the first target time window; L is the number of households connected to TRA2; S is the service life of TRA2;

[0116] The L meets the following conditions:

[0117] LZ<NUM1, then L=0;

[0118] NUM1≤LZ<NUM2, then L=1;

[0119] NUM2≤LZ<NUM3, then L=2;

[0120] NUM3≤LZ<NUM4, then L=3;

[0121] NUM4≤LZ, then L=4;

[0122] NUM1<NUM2<NUM3<NUM4;

[0123] Among them, LZ is the number of households connected to TRA2; NUM1, NUM2, NUM3, NUM4 are preset household number thresholds.

[0124] Here, in order to make the parameters in the target feature vector similar in magnitude, the above L is subjected to data binning.

[0125] S6: Determine the target feature vector N=(E1, F1, E2, F2, …, Ea, Fa, …, Eb, Fb, Pmax, Pmin, L, S) corresponding to TRA2 based on E, F and J;

[0126] S7: Input N into the target AI model to obtain the predicted fire probability U corresponding to TRA2 output by the target AI model within the target time length in the future, where U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+m*Pmaβ+n*Pmin+v*L+w*S; wherein β1, β2,…,βa,…,βb, s1, s2,…,sa,…,sb, m, n, v, w are the parameters obtained by the target AI model after training.

[0127] Example 3

[0128] On the basis of Embodiment 2, before step S6, the method further includes:

[0129] S601: Obtain the estimated temperature set G=(G1, G2, …, Gc, …, Gd) corresponding to TRA2 in the first target time window; c=1, 2, …, d; wherein Gc is the estimated maximum ambient temperature identifier of the cth day after the current time corresponding to TRA2; d is the estimated number of days after the current time.

[0130] At this time, step S6 includes:

[0131] According to E, F, G and J, determine the target feature vector N = (E1, F1, E2, F2,…, Ea, Fa,…, Eb, Fb, G1, G2,…, Gc,…, Gd, Pmax, Pmin, L, S) corresponding to TRA2.

[0132] U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+t1*G1+t2*G2+…+tc*Gc+…+td*Gd+m*Pmaβ+n*Pmin+v*L+w*S; among which, t1, t2,…, tc,…, td are the parameters obtained by the target AI model after training.

[0133] In this embodiment, the estimated maximum ambient temperature identifier of each day within d days after the current time corresponding to TRA2 is obtained, and this is used as a part of the target feature vector. This can reflect the heat dissipation condition of the target main transformer protection panel cabinet under the influence of the maximum ambient temperature within d days after the current time. This is based on the maximum ambient temperature change in a period of time before the current time and relatively short from the current time and the workpiece information change of the target main transformer protection panel cabinet, combined with the estimated maximum ambient temperature for each day within d days after the current time. The time span is longer, including before and after the current time, so that the final determined U is more accurate.

[0134] The method for obtaining the estimated temperature identification set G corresponding to TRA2 in the first target time window is as follows:

[0135] S601-1: Obtain the estimated ambient temperature set GZ=(GZ1, GZ2, ..., GZc, ..., GZd) corresponding to TRA2 in the first target time window; wherein GZc is the estimated maximum ambient temperature of TRA2 corresponding to the current time and the cth day after that;

[0136] S601-2: Determine G according to GZ, where Gc is the temperature identifier corresponding to GZc;

[0137] Gc meets the following criteria:

[0138] GZc<TEMP1, then Gc=0;

[0139] TEMP1≤GZc<TEMP2, then Gc=1;

[0140] TEMP2≤GZc<TEMP3, then Gc=2;

[0141] TEMP3≤GZc<TEMP4, then Gc=3;

[0142] TEMP4≤GZc, then Gc=4;

[0143] TEMP1<TEMP2<TEMP3<TEMP4;

[0144] TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3;

[0145] Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

[0146] In this embodiment, the estimated maximum ambient temperature corresponding to each day within d days after the current time is divided into boxes through the above-mentioned multiple temperature intervals. This is because at different temperatures, the equivalent numerical change of temperature has different effects on the target main transformer protection panel cabinet. For example, when the temperature is below 90°C, it is the normal working temperature range of the main transformer protection panel cabinet. Therefore, the temperature change within this temperature range has basically no effect on the target main transformer protection panel cabinet, but after the temperature reaches 105°C, the increase in temperature will have a greater impact on the main transformer protection panel cabinet. When the temperature rises to 120°C, the life of the main transformer protection panel cabinet is only 2 years. Therefore, in this embodiment, multiple temperature ranges of GZc are determined, and the corresponding final values ​​are different, and the length of the temperature interval will gradually decrease (i.e., TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3), so that the temperature mark can more accurately reflect the impact of its corresponding estimated maximum ambient temperature on TRA2.

[0147] Example 4

[0148] On the basis of Example 3, before step S6, the method further includes:

[0149] S602, obtain the maintenance information set Y=(Y1, Y2, ..., Yg, ..., Yh) corresponding to TRA2 in the second target time window; g=1, 2, ..., h; wherein h is the number of second time periods arranged consecutively in the second target time window; Yg is the maintenance information Yg=(YJg, YGg) corresponding to TRA2 in the g-th second time period; YJg is the number of inspections performed by TRA2 in the g-th second time period; YGg is the workpiece replacement information of the workpiece replaced by TRA2 in the g-th second time period; YGg=(YGg1, YGg2, ..., YGgθ, ..., YGgε); θ=1, 2, ..., ε ; Wherein, YGgθ is the workpiece replacement information of the θth workpiece replaced by TRA2 in the gth second time period; ε is the total number of workpieces replaced included in TRA2; YGgθ=(YGTgθ, YGQgθ); YGTgθ is the workpiece replacement time of the θth workpiece replaced by TRA2 in the gth second time period; YGQgθ is the replacement reason identifier of the θth workpiece replaced by TRA2 in the gth second time period; the length of the second target time window is h*ΔT2, ΔT2 is the length of each second time period; (h*ΔT2)>(b*ΔT1), and ΔT2>ΔT1.

[0150] At this time, step S6 includes:

[0151] According to E, F, G, J and Y, determine the target feature vector N = (E1, F1, E2, F2,…, Ea, Fa,…, Eb, Fb, G1, G2,…, Gc,…, Gd, Y1, Y2,…, Yg,…, Yh, Pmax, Pmin, L, S) corresponding to TRA2.

[0152] U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+π1*Y1+π2*Y2+…+πg*Yg+…+πh*Yh+m*Pmaβ+n*Pmin+v*L+w*S; among which, π1, π2,…, πg,…, πh are the parameters obtained by the target AI model after training.

[0153] In this embodiment, the maintenance information set Y corresponding to TRA2 in the second target time window is obtained, and Y includes the maintenance information corresponding to each second time period. Specifically, the maintenance information includes the number of inspections of TRA2 in each time period, and the workpiece replacement information of TRA2 that has been replaced in each time period. The workpiece replacement information includes the replacement time and replacement reason identifier of each replaced workpiece. The replacement reason identifier is used to identify different replacement reasons, and the replacement reasons include wear, aging, etc. In summary, Y reflects the maintenance status and workpiece replacement details of the main transformer protection panel cabinet corresponding to each second time period of TRA2 in the second target time window. If TRA2 is inspected in a second time period in the second target time window or a key workpiece of TRA2 (the above-mentioned target workpiece, i.e., the relevant workpiece that causes the main transformer protection panel cabinet to spontaneously combust) is replaced and the replacement time is close to the current time, the probability of TRA2 spontaneous combustion will be reduced, otherwise, the probability of TRA2 spontaneous combustion will be increased, so that the target AI model is more accurate when obtaining the predicted probability of fire occurrence U.

[0154] It should be noted that the frequency of maintenance and workpiece replacement is low, so in order to obtain as much maintenance information and workpiece replacement information as possible, the length of the second target time window in this embodiment is much greater than the length of the first target time window; and in order to include as much valid information as possible in each second time period, the length of the second time period is also much greater than the length of the first time period.

[0155] In the present application, the parameter combination method in N is not limited to the above-mentioned implementation mode. As an example: N=(E1, F1, E2, F2, …, Ea, Fa, …, Eb, Fb, G1, G2, …, Gc, …, Gd, Y1, Y2, …, Yg, …, Yh, Pmax, Pmin, L, S) or N=(E1, F1, E2, F2, …, Ea, Fa, …, Eb, Fb, Y1, Y2, …, Yg, …, Yh, Pmax, Pmin, L, S).

[0156] Example 5

[0157] In an exemplary embodiment of the present application, if U is greater than a preset probability threshold in step S7, a prompt message is output.

[0158] In this embodiment, for the target main transformer protection cabinet TRA2 in the target substation located in the main transformer cabinet area, the maximum ambient temperature identification set, the main transformer protection cabinet working information set and the main transformer protection cabinet basic information corresponding to the first target time window are obtained, and the maximum ambient temperature identification set, the main transformer protection cabinet working information set and the main transformer protection cabinet basic information corresponding to the first target time window are used as the target feature vector of TRA2, and the number and end time of the first time period of the time window are controlled at the same time, so that the parameters in the target feature vector can reflect the maximum ambient temperature change of the target main transformer protection cabinet within a period of time shorter than the current time, the weather change, the output power change of the target main transformer protection cabinet when working, the workload change, the service life, the maximum working temperature change and other information. Since TRA2 is located in the main transformer cabinet area, and the substation in the main transformer cabinet area is characterized by high and low peaks in power use, and the main transformer protection cabinet has rest time, so the output power and maximum working temperature change range are large, and the output power of TRA2 during the peak power consumption period (daytime) is greater than the output power of TRA2 during the low power consumption period (nighttime), and the maximum working temperature is the same. According to the maximum ambient temperature, weather type identification, maximum / minimum output power and maximum operating temperature corresponding to each first time period in the first target time window, the heat dissipation of TRA2 can be determined as part of the target feature vector of TRA2, so that the final determined U is more accurate. In addition, basic information such as the number of households connected to TRA2, the maximum power consumption and service life are also important factors that cause TRA2 to spontaneously combust. The more households connected or the greater the maximum power consumption, the greater the current operating load of TRA2, and the greater the possibility of spontaneous combustion. The longer the service life, the more serious the aging of the internal workpieces of TRA2, and the greater the possibility of spontaneous combustion. Therefore, this application uses the above-mentioned maximum ambient temperature identification set, the main transformer protection panel cabinet working information set and the main transformer protection panel cabinet basic information as the target feature vector of TRA2, so that the target AI model is more accurate when obtaining the predicted probability of fire occurrence U. Finally, if U is greater than the preset probability threshold, a prompt message is output to achieve a fire warning for the substation.

[0159] On the basis of the above, the estimated maximum ambient temperature mark of each day within d days after the current time corresponding to TRA2 can also be obtained. This can be used as part of the target feature vector to reflect the heat dissipation of the target main transformer protection panel cabinet under the influence of the maximum ambient temperature within d days after the current time. This is based on the maximum ambient temperature changes in a period of time before the current time and relatively short from the current time and the changes in the workpiece information of the target main transformer protection panel cabinet, combined with the estimated maximum ambient temperature of each day within d days after the current time. The time span is longer, including before and after the current time, so that the final determined U is more accurate.

[0160] In addition, the maintenance information set Y corresponding to TRA2 in the second target time window can also be obtained, and Y includes the maintenance information corresponding to each second time period. The maintenance information includes the number of maintenance of TRA2 in each time period, and the replacement information of the workpieces replaced by TRA2 in each time period. The workpiece replacement information includes the replacement time and replacement reason identification of each replaced workpiece, wherein the replacement reason identification is used to identify different replacement reasons, and the replacement reasons include wear, aging, etc. In summary, Y reflects the maintenance status and workpiece replacement details of the main transformer protection panel cabinet corresponding to each second time period of TRA2 in the second target time window. If, in a second time period of the second target time window, TRA2 is overhauled or a key workpiece of TRA2 (the above-mentioned target workpiece, i.e., the relevant workpiece that causes the spontaneous combustion of the main transformer protection panel cabinet) is replaced and the replacement time is close to the current time, the probability of spontaneous combustion of TRA2 will be reduced, otherwise, the probability of spontaneous combustion of TRA2 will be increased, so that the target AI model is more accurate when obtaining the predicted probability of fire occurrence U.

[0161] It should be noted that the frequency of maintenance and workpiece replacement is low, so in order to obtain as much maintenance information and workpiece replacement information as possible, the length of the second target time window in this embodiment is much greater than the length of the first target time window; and in order to include as much valid information as possible in each second time period, the length of the second time period is also much greater than the length of the first time period.

[0162] Example 6

[0163] In an exemplary embodiment of the present application, if the target area identifier identifies the area where the target substation is located as an industrial power consumption area in step S2, then proceed to step S8.

[0164] S8: Obtain the maximum ambient temperature identification set A=(A1, A2,…, Aa,…, Ab) corresponding to the target main transformer protection cabinet TRA1 in the target substation in the first target time window; a=1, 2,…, b; wherein the target substation is located in the industrial power consumption area; b is the number of first time periods arranged continuously in the first target time window; Aa is the maximum ambient temperature identification corresponding to TRA1 in the ath first time period; the end time of the first target time window is the current time.

[0165] The end time of the first target time window is the current time, which is a period of time close to the current time. The length of the first target time window is b*ΔT1, where ΔT1 is the length of each first time period. The length of the first target window is less than the continuous working time length of the main transformer protection cabinet.

[0166] It should be noted that the target area identifier is used to identify the area type of the area where the target substation is located, and can identify the area where the target substation is located as a main transformer cabinet area or an industrial power area. Step S8 includes the following sub-steps:

[0167] S8-1: Obtain the maximum ambient temperature set AZ=(AZ1, AZ2, ..., AZa, ..., AZb) corresponding to TRA1 in the first target time window; wherein AZa is the maximum ambient temperature corresponding to TRA1 in the ath first time period;

[0168] S8-2: Determine A according to AZ; wherein Aa is the temperature identifier corresponding to AZa;

[0169] Aa meets the following conditions:

[0170] AZa<TEMP1, then Aa=0;

[0171] TEMP1≤AZa<TEMP2, then Aa=1;

[0172] TEMP2≤AZa<TEMP3, then Aa=2;

[0173] TEMP3≤AZa<TEMP4, then Aa=3;

[0174] TEMP4≤AZa, then Aa=4;

[0175] TEMP1<TEMP2<TEMP3<TEMP4;

[0176] TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3;

[0177] Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

[0178] In this embodiment, the maximum ambient temperature corresponding to all the first time periods in the first target time window is divided into boxes through the above-mentioned multiple temperature intervals. This is because at different temperatures, the same numerical change in temperature has different effects on the target main transformer protection cabinet. For example, when the temperature is below 90°C, it is the normal working temperature range of the main transformer protection cabinet. Therefore, the change in temperature within this temperature range has basically no effect on the target main transformer protection cabinet. However, after the temperature reaches 105°C, the increase in temperature will have a greater impact on the main transformer protection cabinet. When the temperature rises to 120°C, the life of the main transformer protection cabinet is only 2 years. Therefore, in this embodiment, multiple temperature ranges of AZa are determined, and the corresponding final values ​​are different, and the length of the temperature interval will gradually decrease (i.e., TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3), so that the temperature mark can more accurately reflect the impact of its corresponding maximum ambient temperature on the target main transformer protection cabinet.

[0179] S9: Obtain a workpiece information set B=(B1, B2, ..., Ba, ..., Bb) corresponding to TRA1 in the first target time window; wherein Ba is the workpiece information corresponding to TRA1 in the ath first time period.

[0180] In some embodiments, Ba=(Ba1, Ba2, …, Bae, …, Baf); e=1, 2, …, f; wherein Bae is the sub-workpiece information corresponding to the workpiece of the e-th target type in TRA1 in the a-th first time period; f is the number of target types; Bae=(NGae, ZGae, EDae); NGae is the working years corresponding to the target workpiece in the e-th target type in TRA1 in the a-th first time period; the target workpiece in the e-th target type is the workpiece with the highest probability of scrapping among the workpieces of the e-th target type; ZGae is the maximum working years corresponding to the target workpiece in the e-th target type in TRA1 in the a-th first time period; EDae is the rated ambient temperature corresponding to the target workpiece in the e-th target type in TRA1.

[0181] The scrap probability BF of the above target workpiece meets the following conditions: BF=YEAR1 / YEARmax; where YEAR1 is the working life of the target workpiece; and YEARmax is the maximum working life of the target workpiece.

[0182] It should be noted that since the maximum service life of the main transformer protection panel cabinet is different at different working temperatures, overheating of the main transformer protection panel cabinet will lead to a reduction in the maximum service life, so the ZGae in this application is obtained by calculation rather than directly obtained according to the workpiece manual. The specific acquisition method is as follows: obtain the average operating temperature of TRA1 in the ath first time period, traverse the preset mapping table based on the average operating temperature of TRA1 in the ath first time period, and determine ZGae. The calculated ZGae is used as part of the target vector, taking into account the impact of the actual operating temperature on the maximum service life of the workpiece. Compared with the method of directly obtaining it according to the workpiece manual, it can better reflect the actual maximum service life of each workpiece. Furthermore, the target AI model is more accurate in obtaining the predicted probability V of occurrence of special circumstances.

[0183] In this embodiment, when determining the factors in the workpiece information set, the workpiece type corresponding to the relevant workpiece that may cause spontaneous combustion of the main transformer protection panel cabinet in TRA1 is first taken as the target type; then the workpiece with the highest probability of scrapping is selected from all the workpieces of each target type as the target workpiece of the target type, and finally the working years, maximum working years and rated temperature identification of the target workpiece corresponding to each target type in each first time period are used as the workpiece information set corresponding to TRA1 in the first target time window, which characterizes the working years status and optimal working temperature of the target workpiece in TRA1 that may cause spontaneous combustion within a relatively short period of time at the current time, and then determines the aging degree of the target workpiece and the difference between the actual working temperature and the optimal working temperature, and determines whether it will induce spontaneous combustion of the main transformer protection panel cabinet, so that the target AI model is more accurate when obtaining the predicted probability V of occurrence of special circumstances.

[0184] In addition, the maximum service life of the above-mentioned target workpiece is a maximum service life determined based on the average working temperature of the current first time period, rather than being directly determined according to the instructions of the workpiece. The influence of the actual working temperature of the workpiece on the maximum service life of the workpiece is taken into consideration, and the maximum service life of the target workpiece determined in this way is more accurate.

[0185] S10: Based on A and B, determine the target feature vector M=(A1, B1, A2, B2, …, Aa, Ba, …, Ab, Bb) corresponding to TRA1.

[0186] In some embodiments, based on A and B, the target feature vector M corresponding to TRA1 is determined.

[0187] S11: Input M into the target AI model to obtain the predicted probability V of occurrence of special circumstances corresponding to TRA1 output by the target AI model within the target time length in the future; V meets the following conditions: V=x1*A1+y1*B1+x2*A2+y2*B2+…+xa*Aa+ya*Ba+…+xb*Ab+yb*Bb; wherein, x1, x2,…, xa,…, xb, y1, y2,…, ya,…, yb are the parameters obtained by the target AI model after training.

[0188] S12: If V is greater than a preset probability threshold, a prompt message is output.

[0189] Example 7

[0190] In an exemplary embodiment of the present application, before step S10, the method further includes:

[0191] S101: Obtain the estimated temperature identification set C=(C1, C2, ..., Cc, ..., Cd) corresponding to TRA1 in the first target time window; c=1, 2, ..., d; wherein Cc is the estimated maximum ambient temperature identification of the cth day after the current time corresponding to TRA1; d is the estimated number of days after the current time;

[0192] At this time, the step S10 includes:

[0193] Based on A, B and C, determine the target feature vector M=(A1, B1, A2, B2,…, Aa, Ba,…, Ab, Bb, C1, C2,…, Cc,…, Cd) corresponding to TRA1.

[0194] V meets the following conditions:

[0195] V=x1*A1+y1*B1+x2*A2+y2*B2+…+xa*Aa+ya*Ba+…+xb*Ab+yb*Bb+z1*C1+z2*C2+…+zc*Cc+…+zd*Cd; wherein z1, z2,…, zc,…, zd are the parameters of the target AI model obtained after training.

[0196] In this embodiment, the estimated maximum ambient temperature identifier of each day within d days after the current time corresponding to TRA1 is obtained, and this is used as a part of the target feature vector. This can reflect the heat dissipation condition of the target main transformer protection panel cabinet under the influence of the maximum ambient temperature within d days after the current time. This is based on the maximum ambient temperature change in a period of time before the current time and relatively short from the current time and the workpiece information change of the target main transformer protection panel cabinet, combined with the estimated maximum ambient temperature for each day within d days after the current time. The time span is longer, including before and after the current time, so that the finally determined V is more accurate.

[0197] The method for obtaining the estimated temperature identification set C corresponding to TRA1 in the first target time window is as follows:

[0198] S101-1, obtaining the estimated ambient temperature set CZ=(CZ1, CZ2, ..., CZc, ..., CZd) corresponding to TRA1 in the first target time window; wherein CZc is the estimated maximum ambient temperature of TRA1 corresponding to the current time c days later;

[0199] S101-2, determining C according to CZ; wherein Cc is the temperature identifier corresponding to CZc;

[0200] Cc meets the following conditions:

[0201] CZc<TEMP1, then Cc=0;

[0202] TEMP1≤CZc<TEMP2, then Cc=1;

[0203] TEMP2≤CZc<TEMP3, then Cc=2;

[0204] TEMP3≤CZc<TEMP4, then Cc=3;

[0205] TEMP4≤CZc, then Cc=4;

[0206] TEMP1<TEMP2<TEMP3<TEMP4;

[0207] TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3;

[0208] Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

[0209] In this embodiment, the estimated maximum ambient temperature corresponding to each day within d days after the current time is divided into boxes through the above-mentioned multiple temperature intervals. This is because at different temperatures, the equivalent numerical change of temperature has different effects on the target main transformer protection panel cabinet. For example, when the temperature is below 90°C, it is the normal working temperature range of the main transformer protection panel cabinet. Therefore, the temperature change in this temperature range has basically no effect on the target main transformer protection panel cabinet, but after the temperature reaches 105°C, the increase in temperature will have a greater impact on the main transformer protection panel cabinet. When the temperature rises to 120°C, the life of the main transformer protection panel cabinet is only 2 years. Therefore, in this embodiment, multiple temperature ranges of CZc are determined, and the corresponding final values ​​are different, and the length of the temperature interval will gradually decrease (i.e., TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3), so that the temperature mark can more accurately reflect the impact of its corresponding estimated maximum ambient temperature on the target main transformer protection panel cabinet.

[0210] Example 8

[0211] In an exemplary embodiment of the present application, before step S10, the method further includes:

[0212] S102: Obtain the maintenance information set X=(X1, X2, …, Xg, …, Xh) corresponding to TRA1 in the second target time window; g=1, 2, …, h; wherein h is the number of second time periods arranged continuously in the second target time window; Xg is the maintenance information corresponding to TRA1 in the g-th second time period; Xg=(XJg, XGg); XJg is the number of inspections performed by TRA1 in the g-th second time period; XGg is the workpiece replacement information of the workpiece replaced by TRA1 in the g-th second time period; XGg=(XGg1, XGg2, …, XGgi, …, XGgj); i=1, 2, …, j; XGgi is the workpiece replacement information of the i-th workpiece replaced by TRA1 in the g-th second time period; j is the total number of workpieces replaced by TRA1; XGgi=(XGTgi, XGQgi); wherein XGTgi is the workpiece replacement time of the i-th workpiece replaced by TRA1 in the g-th second time period; XGQgi is the replacement reason identifier of the i-th workpiece replaced by TRA1 in the g-th second time period; the length of the second target time window is h*ΔT2, ΔT2 is the length of each second time period; (h*ΔT2)>(b*ΔT1), and ΔT2>ΔT1.

[0213] At this time, the step S10 includes:

[0214] According to A, B, C and X, determine the target feature vector M=(A1, B1, A2, B2,…, Aa, Ba,…, Ab, Bb, C1, C2,…, Cc,…, Cd, X1, X2,…, Xg,…, Xh) corresponding to TRA1.

[0215] V satisfies the following condition V=x1*A1+y1*B1+x2*A2+y2*B2+…+xa*Aa+ya*Ba+…+xb*Ab+yb*Bb+z1*C1+z2*C2+…+zc*Cc+…+zd*Cd+k1*X1+k2*X2+…+kg*Xg+…+kh*Xh; among which, k1, k2,…, kg,…, kh are the parameters obtained by the target AI model after training.

[0216] In this embodiment, the maintenance information set X corresponding to TRA1 in the second target time window is obtained, and X includes the maintenance information corresponding to each second time period. Specifically, the maintenance information includes the number of inspections of TRA1 in each time period, and the workpiece replacement information of the workpieces replaced by TRA1 in each time period. Here, the workpiece replacement information includes the replacement time and replacement reason identifier of each replaced workpiece, wherein the replacement reason identifier is used to identify different replacement reasons, and the replacement reasons include wear, aging, etc. In summary, X reflects the maintenance status and workpiece replacement details of the main transformer protection panel cabinet corresponding to each second time period of TRA1 in the second target time window. If, in a second time period of the second target time window, TRA1 is inspected or a key workpiece of TRA1 (the above-mentioned target workpiece, i.e., the relevant workpiece that causes the main transformer protection panel cabinet to spontaneously combust) is replaced and the replacement time is close to the current time, the probability of TRA1 spontaneous combustion will be reduced, otherwise, the probability of TRA1 spontaneous combustion will be increased, so that the target AI model is more accurate when obtaining the predicted probability V of occurrence of special circumstances.

[0217] It should be noted that the frequency of maintenance and workpiece replacement is low, so in order to obtain as much maintenance information and workpiece replacement information as possible, the length of the second target time window in this embodiment is much greater than the length of the first target time window; and in order to include as much valid information as possible in each second time period, the length of the second time period is also much greater than the length of the first time period.

[0218] In the present application, the parameter combination method in M ​​is not limited to the above-mentioned implementation mode. As an example: M=(A1, B1, A2, B2,…, Aa, Ba,…, Ab, Bb, C1, C2,…, Cc,…, Cd, X1, X2,…, Xg,…, Xh) or M=(A1, B1, A2, B2,…, Aa, Ba,…, Ab, Bb, X1, X2,…, Xg,…, Xh).

[0219] The present embodiment provides a method for early warning of special situations in a substation. For a target main transformer protection panel cabinet TRA1 in a target substation in an industrial power consumption area, the maximum ambient temperature identification set and workpiece information set corresponding to the first target time window are obtained, and the maximum ambient temperature identification set and workpiece information set are used as the target feature vector of the target main transformer protection panel cabinet. At the same time, the number and end time of the first time period of the time window are controlled, so that the parameters in the target feature vector can reflect the maximum ambient temperature change of the target main transformer protection panel cabinet in a period of time shorter than the current time and the workpiece information change of the target main transformer protection panel cabinet. Here, since TRA1 is located in the industrial power consumption area, and the characteristics of the substation in the industrial power consumption area are continuous high-power power consumption and high operating temperature, and in the case of continuous high-power power consumption and high operating temperature, the ambient temperature plays a vital role in the heat dissipation of the main transformer protection panel cabinet. If the maximum ambient temperature is lower, that is, the temperature difference between the operating temperature of the main transformer protection panel cabinet and the maximum ambient temperature is greater, the more heat the main transformer protection panel cabinet can conduct to the outside world, and it is less likely to spontaneously combust and cause a substation fire. Therefore, in this application, the maximum ambient temperature identification set is obtained as part of the TRA1 target feature vector, so that the final determined V is more accurate. In addition, when TRA1 continues to use high power, that is, when the power change amplitude is not large, the workpiece information that characterizes the internal workpiece status of TRA1 is also an important factor causing TRA1 to spontaneously combust. Therefore, the workpiece information set of the target feature vector corresponding to TRA1 in this application includes the working years, maximum working years and rated temperature identification of the target workpiece corresponding to each target type in each first time period, characterizing the working years and optimal working temperature of the target workpiece in TRA1 that may cause spontaneous combustion within a relatively short period of time at the current time, and then determining the aging degree of the target workpiece and the difference between the actual working temperature and the optimal working temperature, and determining whether it will induce spontaneous combustion of the main transformer protection panel cabinet, so that the target AI model is more accurate when obtaining the predicted probability V of occurrence of special circumstances.

[0220] The present application can also obtain the estimated maximum ambient temperature identifier of each day within d days after the current time corresponding to TRA1, and use it as part of the target feature vector, which can reflect the heat dissipation of the target main transformer protection panel cabinet under the influence of the maximum ambient temperature within d days after the current time. It is based on the maximum ambient temperature changes in a period of time before the current time and relatively short from the current time and the changes in the workpiece information of the target main transformer protection panel cabinet, combined with the estimated maximum ambient temperature for each day within d days after the current time, and the time span is longer, including before the current time and after the current time, so that the final determined V is more accurate.

[0221] In addition, the maintenance information set X corresponding to TRA1 in the second target time window can also be obtained, and X includes the maintenance information corresponding to each second time period. Specifically, the maintenance information includes the number of inspections of TRA1 in each time period, and the workpiece replacement information of the workpieces replaced by TRA1 in each time period. Here, the workpiece replacement information includes the replacement time and replacement reason identifier of each replaced workpiece, wherein the replacement reason identifier is used to identify different replacement reasons, and the replacement reasons include wear, aging, etc. In summary, X reflects the maintenance status and workpiece replacement details of the main transformer protection panel cabinet corresponding to each second time period of TRA1 in the second target time window. If, in a second time period of the second target time window, TRA1 is inspected or a key workpiece of TRA1 (the above-mentioned target workpiece, i.e., the relevant workpiece that causes the spontaneous combustion of the main transformer protection panel cabinet) is replaced and the replacement time is close to the current time, the probability of spontaneous combustion of TRA1 will be reduced, otherwise, the probability of spontaneous combustion of TRA1 will be increased, so that the target AI model is more accurate when obtaining the predicted probability V of occurrence of special circumstances.

[0222] Example 9

[0223] In an exemplary embodiment of the present application, the target AI model is obtained according to the following steps:

[0224] S7-1: Obtain the first data set D=(D1, D2, …, Dδ, …, Dζ); δ=1, 2, …, ζ; wherein ζ is the number of first-class main transformer protection cabinets; the first-class main transformer protection cabinet is the main transformer protection cabinet whose current state is a fire; Dδ is the first sub-data set corresponding to the δth first-class main transformer protection cabinet; Dδ=(Dδ1, Dδ2, …, Dδp, …, Dδq); p=1, 2, …, q; q is the first time window of the dth first-class main transformer protection cabinet The number of days corresponding to the target time length is q; Dδp is the feature vector corresponding to the δth first-class main transformer protection panel cabinet in the pth first time window; the end time of the first time window corresponding to Dδp is the time point corresponding to (p-1)*24 hours before the current state of the δth first-class main transformer protection panel cabinet is determined to be a fire, and the time from the zero point of the day when the fire occurred is the same as the length of the target time window; the probability of the occurrence of the marked anomaly corresponding to each feature vector in D is 1;

[0225] S7-2: Obtain the second data set H=(H1,H2,…,Hσ,…,Hr);σ=1,2,…,r;wherein, r is the number of the second-category main transformer protection cabinets;the second-category main transformer protection cabinets are the main transformer protection cabinets whose current state is that no fire has occurred;Hσ is the feature vector corresponding to the σ-th second-category target main transformer protection cabinet in the second time window;the second time window has the same length as the target time window;the probability of occurrence of the marked abnormality corresponding to each feature vector in H is 0;

[0226] S7-3: Train the initial AI model according to D and H to obtain the target AI model.

[0227] Since there are relatively few main transformer protection cabinets where fires have occurred, in order to improve the accuracy of the target AI model when obtaining negative samples, the present application needs to perform sample enhancement on the negative samples. For the same main transformer protection cabinet where a fire has occurred, multiple first time windows are determined, each first time window corresponds to a feature vector, the length of the first time window is equal to the length of the first target time window, and the end time of each first time window is different, but the end time of each first time window is within the target time length. Specifically, the end time of the pth first time window is before midnight on the day of the fire and the time point corresponding to the length of (p-1)*24 hours (p is the pth first time window) from midnight on the day of the fire is the end time of the pth first time window. Therefore, it can be ensured that the time when the fire occurs in the main transformer protection cabinet is within the target time length after the end of each first time window, thereby ensuring the validity of the negative samples and enhancing the negative samples, thereby improving the accuracy of the target AI model.

[0228] When obtaining positive samples, since most of the main transformer protection cabinets are normal and no fire has occurred, sample enhancement is not required, so several second-class main transformer protection cabinets (main transformer protection cabinets where no fire has occurred) are selected to obtain the corresponding feature vectors of each second-class main transformer protection cabinet in the second time window, and the probability of abnormal occurrence of the mark corresponding to each feature vector is 0. Here, the second time window has the same length as the first target time window, and the end time of the second time window is any time point before the current time and the length from the current time is less than the target time length.

[0229] Example 10

[0230] In some optional implementations of some embodiments, the target AI model may also be obtained according to the following steps:

[0231] S7-4: Obtain the first data set D=(D1, D2, …, Dδ, …, Dζ); δ=1, 2, …, ζ; wherein ζ is the number of first-class main transformer protection cabinets; the first-class main transformer protection cabinet is the main transformer protection cabinet whose current state is a fire; Dδ is the first sub-data set corresponding to the δth first-class main transformer protection cabinet; Dδ=(Dδ1, Dδ2, …, Dδp, …, Dδq); p=1, 2, …, q; q is the number of time windows of the dth first-class main transformer protection cabinet, and q is the number of days corresponding to the target time length; Dδp is the number of time windows of the δth first-class main transformer protection cabinet in the pth time window. The feature vector corresponding to the first time window; the end time of the first time window corresponding to Dδp is the time point corresponding to (p-1)*24 hours before the current state of the δth first-class main transformer protection cabinet is determined to be a fire, and the time from zero o'clock on the day of the fire is the same as the length of the target time window; the probability of occurrence of the marked anomaly corresponding to Dδp is (tag11=0, tag12=0, …, tag1p=1, …, tag1q=0); where tag1p is the probability of a fire occurring on the pth day after the end time of the first time window corresponding to Dδp.

[0232] S7-5: Obtain the second data set H=(H1, H2, …, Hσ, …, Hr); σ=1, 2, …, r; wherein r is the number of second-category main transformer protection cabinets; the second-category main transformer protection cabinets are main transformer protection cabinets whose current state is that no fire has occurred; Hσ is the feature vector corresponding to the σth second-category target main transformer protection cabinet in the second time window; the second time window has the same length as the target time window; the probability of occurrence of the marked abnormality corresponding to each feature vector in H is 0.

[0233] S7-6: Train the initial AI model according to D and H to obtain the target AI model.

[0234] The labeling method for the feature vector labels is different from that in the previous embodiment. The labels are respectively marked according to the probability of a fire occurring every day after the end time of the first time window corresponding to Dδp. As the labels of the feature vectors, compared with the previous embodiment, the model is trained more accurately using the probability of a fire occurring every day within the target time length.

[0235] It should be noted that the above-mentioned fire occurrence probability, abnormality occurrence probability and special situation occurrence probability can all represent the predicted probability of a fire occurring in a substation.

[0236] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0237] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0238] The above descriptions are only optional embodiments of the present invention, and are not intended to limit the patent scope of the present invention. All equivalent structural changes made using the contents of the present invention's specification and drawings, or directly / indirectly applied in other related technical fields, are included in the patent protection scope of the present invention.

Claims

1. An electrical fire early warning method based on multi-sensor fusion, characterized in that: Applied to the electrical fire early warning system based on multi-sensor fusion, the electrical fire early warning system based on multi-sensor fusion includes a variety of sensors: used to monitor the working status and environmental parameters of electrical equipment in real time; Data acquisition module: used to collect data from each sensor and perform preliminary data processing; Data fusion processing unit: uses data fusion algorithm to comprehensively analyze the data of each sensor and identify potential fire risks; Early warning decision module: Based on the analysis results of the data fusion processing unit, it determines whether there is a fire risk and decides whether to issue an early warning signal; Communication interface: realize remote monitoring and data transmission functions, and support linkage with other security systems; User interface: Provide users with an intuitive operation interface and early warning information display; The electrical fire early warning method based on multi-sensor fusion includes the following steps: S1: Obtain the target area identifier of the area where the target substation is located; S2: If the target area identifier identifies the area where the target substation is located as a main transformer area, proceed to step S3; S3: Obtain the maximum ambient temperature identifier set E=(E1, E2, ..., Ea, ..., Eb) corresponding to the target main transformer protection cabinet TRA2 in the target substation in the first target time window, where a=1, 2, ..., b, b is the number of first time periods arranged continuously in the first target time window, Ea is the maximum ambient temperature identifier corresponding to TRA2 in the ath first time period, the end time of the first target time window is the current time, and the length of the first target time window is b*ΔT1, where ΔT1 is the length of each first time period; S4: Obtain the main transformer protection cabinet working information set F=(F1, F2, ..., Fa, ..., Fb) corresponding to TRA2 in the first target time window, where Fa is the main transformer protection cabinet working information corresponding to TRA2 in the a-th first time period, Fa=(PFa, TFa, QFa), PFa is the maximum power consumption of TRA2 in the a-th first time period, TFa is the maximum operating temperature of TRA2 in the a-th first time period, and QFa is the weather type identifier corresponding to TRA2 in the a-th first time period; S5: Get the basic information of the main transformer protection cabinet of TRA2 J = (Pmax, Pmin, L, S), where Pmax is the maximum output power of TRA2 in the first target time window, Pmin is the minimum output power of TRA2 in the first target time window, L is the number of households connected to TRA2, S is the service life of TRA2, and L meets the following conditions: LZ<NUM1, then L=0; NUM1≤LZ<NUM2, then L=1; NUM2≤LZ<NUM3, then L=2; NUM3≤LZ<NUM4, then L=3; NUM4≤LZ, then L=4; NUM1<NUM2<NUM3<NUM4; Wherein, LZ is the number of households connected to TRA2; NUM1, NUM2, NUM3, NUM4 are the preset household number thresholds; S6: Determine the target feature vector N=(E1, F1, E2, F2, …, Ea, Fa, …, Eb, Fb, Pmax, Pmin, L, S) corresponding to TRA2 based on E, F and J; S7: Input N into the target AI model to obtain the predicted fire probability U corresponding to the target time length in the future output by TRA2 of the target AI model, where U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+m*Pmaβ+n*Pmin+v*L+w*S; wherein β1, β2,…,βa,…,βb, s1, s2,…,sa,…,sb, m, n, v, w are the parameters obtained by the target AI model after training. If U is greater than the preset probability threshold, a prompt message is output.

2. The electrical fire early warning method based on multi-sensor fusion according to claim 1 is characterized in that: The step S3 includes the following sub-steps: S3-1: Obtain the maximum ambient temperature set EZ=(EZ1, EZ2, ..., EZa, ..., EZb) corresponding to TRA2 in the first target time window, where EZa is the maximum ambient temperature corresponding to TRA2 in the ath first time period; S3-2: Determine E according to EZ, where Ea is the temperature identifier corresponding to EZa; Ea in S3-2 meets the following conditions: EZa<TEMP1, then Ea=0; TEMP1≤EZa<TEMP2, then Ea=1; TEMP2≤EZa<TEMP3, then Ea=2; TEMP3≤EZa<TEMP4, then Ea=3; TEMP4≤EZa, then Ea=4; TEMP1<TEMP2<TEMP3<TEMP4; TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3; Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

3. The electrical fire early warning method based on multi-sensor fusion according to claim 2 is characterized in that: Before step S6, the method further includes the following steps: S601: Obtain the estimated temperature set G=(G1, G2, ..., Gc, ..., Gd) corresponding to TRA2 in the first target time window; c=1, 2, ..., d; wherein Gc is the estimated maximum ambient temperature identifier of the cth day after the current time corresponding to TRA2; d is the estimated number of days after the current time; Then step S6 comprises: Determine the target feature vector N=(E1, F1, E2, F2, …, Ea, Fa, …, Eb, Fb, G1, G2, …, Gc, …, Gd, Pmax, Pmin, L, S) corresponding to TRA2 according to E, F, G and J; U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+t1*G1+t2*G2+…+tc*Gc+…+td*Gd+m*Pmaβ+n*Pmin+v*L+w*S; among which, t1, t2,…, tc,…, td are the parameters obtained by the target AI model after training.

4. The electrical fire early warning method based on multi-sensor fusion according to claim 3 is characterized in that: The method for obtaining the estimated temperature identification set G corresponding to TRA2 in the first target time window is as follows: S601-1: Obtain the estimated ambient temperature set GZ=(GZ1, GZ2, ..., GZc, ..., GZd) corresponding to TRA2 in the first target time window; wherein GZc is the estimated maximum ambient temperature of TRA2 corresponding to the current time and the cth day after that; S601-2: Determine G according to GZ, where Gc is the temperature identifier corresponding to GZc; Gc meets the following criteria: GZc<TEMP1, then Gc=0; TEMP1≤GZc<TEMP2, then Gc=1; TEMP2≤GZc<TEMP3, then Gc=2; TEMP3≤GZc<TEMP4, then Gc=3; TEMP4≤GZc, then Gc=4; TEMP1<TEMP2<TEMP3<TEMP4; TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3; Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

5. The electrical fire early warning method based on multi-sensor fusion according to claim 3 is characterized in that: Before step S6, the method further includes: S602, obtaining a maintenance information set Y=(Y1, Y2, ..., Yg, ..., Yh) corresponding to TRA2 in the second target time window; g=1, 2, ..., h; h is the number of second time periods arranged continuously in the second target time window, Yg is the maintenance information corresponding to TRA2 in the g-th second time period Yg=(YJg, YGg), YJg is the number of inspections performed by TRA2 in the g-th second time period, YGg is the workpiece replacement information of the workpiece replaced by TRA2 in the g-th second time period, YGg=(YGg1, YGg2, ..., YGgθ, ..., YGgε), θ=1, 2, ... , ε; YGgθ is the workpiece replacement information of the θth workpiece replaced by TRA2 in the gth second time period, ε is the total number of workpieces replaced in TRA2, YGgθ=(YGTgθ, YGQgθ); YGTgθ is the replacement time of the θth workpiece replaced by TRA2 in the gth second time period; YGQgθ is the replacement reason identifier of the θth workpiece replaced by TRA2 in the gth second time period, the length of the second target time window is h*ΔT2, ΔT2 is the length of each second time period, (h*ΔT2)>(b*ΔT1), and ΔT2>ΔT1; Then step S6 comprises: Determine the target feature vector N=(E1, F1, E2, F2, …, Ea, Fa, …, Eb, Fb, G1, G2, …, Gc, …, Gd, Y1, Y2, …, Yg, …, Yh, Pmax, Pmin, L, S) corresponding to TRA2 according to E, F, G, J and Y; U meets the following conditions: U=β1*E1+s1*F1+β2*E2+s2*F2+…+βa*Ea+sa*Fa+…+βb*Eb+sb*Fb+π1*Y1+π2*Y2+…+πg*Yg+…+πh*Yh+m*Pmaβ+n*Pmin+v*L+w*S; π1, π2,…, πg,…, πh are the parameters obtained by the target AI model after training.

6. The electrical fire early warning method based on multi-sensor fusion according to claim 3 is characterized in that: If the target area identifier in S2 identifies the area where the target substation is located as an industrial power consumption area, then proceed to step S8; S8: Obtain the maximum ambient temperature identification set A=(A1, A2,…, Aa,…, Ab) corresponding to the target main transformer protection cabinet TRA1 in the target substation in the first target time window; a=1, 2,…, b; the target substation is located in the industrial power consumption area, b is the number of first time periods arranged continuously in the first target time window, Aa is the maximum ambient temperature identification corresponding to TRA1 in the ath first time period, and the end time of the first target time window is the current time.

7. The electrical fire early warning method based on multi-sensor fusion according to claim 6 is characterized in that: The S8 comprises the following sub-steps: S8-1: Obtain the maximum ambient temperature set AZ=(AZ1, AZ2, ..., AZa, ..., AZb) corresponding to TRA1 in the first target time window; wherein AZa is the maximum ambient temperature corresponding to TRA1 in the ath first time period; S8-2: Determine A according to AZ, where Aa is the temperature identifier corresponding to AZa; Aa meets the following conditions: AZa<TEMP1, then Aa=0; TEMP1≤AZa<TEMP2, then Aa=1; TEMP2≤AZa<TEMP3, then Aa=2; TEMP3≤AZa<TEMP4, then Aa=3; TEMP4≤AZa, then Aa=4; TEMP1<TEMP2<TEMP3<TEMP4; TEMP2-TEMP1>TEMP3-TEMP2>TEMP4-TEMP3; Among them, TEMP1, TEMP2, TEMP3, and TEMP4 are preset temperature thresholds.

8. The electrical fire early warning method based on multi-sensor fusion according to claim 7 is characterized in that: The following steps are also included: S9: Obtain a workpiece information set B=(B1, B2, ..., Ba, ..., Bb) corresponding to TRA1 in the first target time window, where a=1, 2, ..., b, and Ba is the workpiece information corresponding to TRA1 in the ath first time period; S10: According to A and B, determine the target feature vector M=(A1, B1, A2, B2, …, Aa, Ba, …, Ab, Bb) corresponding to TRA1; S11: According to A and B, determine the target feature vector M corresponding to TRA1, and input M into the target AI model to obtain the predicted probability V of occurrence of special circumstances corresponding to TRA1 output by the target AI model within the target time length in the future; V meets the following conditions: V=x1*A1+y1*B1+x2*A2+y2*B2+…+xa*Aa+ya*Ba+…+xb*Ab+yb*Bb; wherein x1, x2, …, xa, …, xb, y1, y2, …, ya, …, yb are the parameters of the target AI model obtained after training; S12: If V is greater than a preset probability threshold, a prompt message is output.

9. The electrical fire early warning method based on multi-sensor fusion according to claim 1, characterized in that: The sensors include a smoke sensor, a temperature sensor, a current sensor and a voltage sensor.

Images