A method for analyzing the electrical load of power supply in a UAV fire fighting system
By building environmental and load analysis models, representative feature records are selected and electrical load parameters of drone fire protection system power supply are monitored in real time, which solves the problem that cannot be quickly and accurately analyzed in the existing technology, and realizes the ability to detect abnormalities in a timely manner and take measures in a timely manner. .
Patent Information
- Application Number
- CN202411288839.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-14
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-14
AI Technical Summary
The existing electrical load analysis methods cannot quickly and accurately analyze whether there are abnormalities in the electrical load of the drone fire protection system power supply, resulting in the inability to detect abnormalities in time and take measures.
By building an environmental analysis model and a load analysis model, the power and environmental parameters of the drone are monitored in real time, representative feature records are selected, analyzed and issued corresponding levels of early warnings.
It realizes rapid and accurate analysis of whether there are abnormalities in the electrical load of the drone fire protection system power supply, timely discover abnormalities and take measures, improving the analysis efficiency and accuracy.
Smart Images

Figure CN118818367B_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the field of load analysis methods, and in particular to an electrical load analysis method for a power supply of a drone fire fighting system. Background Art
[0002] The drone fire-fighting system refers to a complete system that uses drone technology in the field of firefighting and rescue. The system integrates drone platforms, information collection systems, ground control systems, and a variety of fire-fighting and rescue equipment, providing a new solution for firefighting work.
[0003] In order to ensure stability during the operation of the drone fire fighting system, the power supply electrical load analysis is an indispensable and important part of electrical engineers in the design and operation and maintenance of power systems. This process involves an in-depth understanding of the load characteristics in the power system, data collection, analysis, and the formulation of management strategies based on the analysis results.
[0004] The existing electrical load analysis method has certain defects and cannot quickly and accurately analyze whether there is an abnormality in the electrical load of the power supply of the UAV fire fighting system, and thus cannot detect the abnormality in time and take measures. Therefore, those skilled in the art provide a method for analyzing the electrical load of the power supply of the UAV fire fighting system to solve the problems raised in the above background technology. Summary of the invention
[0005] The purpose of the present invention is to provide a method for analyzing the electrical load of the power supply of a drone fire fighting system, which can quickly and accurately analyze whether there is any abnormality in the electrical load of the power supply of the drone fire fighting system, and timely discover the abnormality when it occurs so as to facilitate taking measures to solve the problems raised in the above background technology.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] A method for analyzing the electrical load of a power supply of a UAV fire fighting system comprises the following steps:
[0008] Load data collection, i.e. real-time monitoring and collection of power parameters of the UAV firefighting system by using a monitoring device, where the power parameters include real-time current, voltage and power;
[0009] Environmental data collection, that is, real-time monitoring and collection of environmental parameters of the current drone environment through sensors, where environmental parameters include the drone's altitude, temperature, humidity, wind direction and wind speed;
[0010] Load characteristic analysis: first build an environmental analysis model, select representative characteristic records from previous flight records, then build a load analysis model and output the analysis results;
[0011] Based on the analysis results, graded warnings are given and alarms of corresponding levels are issued.
[0012] As a further solution of the present invention: the specific analysis process of the environmental analysis model is:
[0013] The current wind direction collected is marked as A1, the current flight direction of the drone is marked as A2, and the angle between A1 and A2 is marked as α real-time;
[0014] The angle between the wind direction and the flight direction of the UAV in each record in the previous flight record is marked as αi, i = 1···n, where n is a positive integer;
[0015] Calculate the difference between α real-time and αi, count the absolute value of the difference between α real-time and each αi and mark it as ;
[0016] from Filter out the smallest 100 values, and then filter out the flight records corresponding to these 100 values as initial feature records;
[0017] A secondary screening is performed based on the initial feature records to obtain the final representative feature records.
[0018] As a further solution of the present invention: the specific process of performing secondary screening based on the initial feature record is:
[0019] The one hundred flight records in the initial feature record are marked as Bj, j = 1···100;
[0020] Then extract the altitude, temperature, humidity and wind speed of the drone in this flight record from Bj, and mark the altitude of the drone as Hj, the temperature as Cj, the humidity as Dj, and the wind speed as Ej;
[0021] Generate the radar map Pj corresponding to Bj based on the altitude Hj, temperature Cj, humidity Dj and wind force Ej of the drone;
[0022] The real-time collected data of the current drone’s altitude is marked as h, the temperature is marked as c, the humidity is marked as d, and the wind speed is marked as e, and a radar map p of the current drone’s environment is generated;
[0023] Compare p and Pj for similarity. If the similarity between p and Pj is greater than 90%, Pj is planned to the first sequence. If the similarity between p and Pj is greater than 80% and less than or equal to 90%, Pj is planned to the second sequence. If the similarity between p and Pj is greater than 70% and less than or equal to 80%, Pj is planned to the third sequence. If the similarity between p and Pj is less than or equal to 70%, Pj is planned to the fourth sequence.
[0024] The number of Pj in the first sequence is marked as F1, the number of Pj in the second sequence is marked as F2, the number of Pj in the third sequence is marked as F3, and the number of preset feature records is marked as f;
[0025] If F1≥f, the flight records Bj corresponding to f radar charts Pj are selected from the first sequence as the final representative feature records. If F1<f, proceed to the next step.
[0026] If (F1+F2)≥f, select 2f flight records Bj corresponding to radar charts Pj from the first and second sequences as the final representative feature records. If the number of radar charts Pj in the first and second sequences does not reach 2f, supplement them from the third sequence. If the number of Pj in the third sequence still does not reach 2f, continue to supplement from the fourth sequence. If (F1+F2)<f, proceed to the next step.
[0027] If (F1+F2+F3)≥f, the flight records Bj corresponding to 3f radar charts Pj are selected from the first sequence, the second sequence and the third sequence as the final representative feature records. If the number of radar charts Pj in the first sequence, the second sequence and the third sequence does not reach 3f, they are supplemented from the fourth sequence; if (F1+F2+F3)<f, it means that the analysis result of this environmental analysis model is abnormal.
[0028] As a further solution of the present invention: when selecting feature records corresponding to the radar chart Pj from the first sequence, the second sequence, the third sequence and the fourth sequence, the radar charts with higher similarity rankings in the sequence are preferentially selected.
[0029] As a further solution of the present invention: the specific analysis process of the load analysis model is:
[0030] The representative feature records analyzed by the environmental analysis model are marked as Gm, m = 1···k, where k is a positive integer;
[0031] Extract the power parameters of the UAV firefighting system during this flight from Gm, and mark the extracted current as Qm, voltage as Um, and power as Wm;
[0032] The current, voltage and power of the drone firefighting system monitored in real time are marked as q, u and w respectively;
[0033] If q, u, and w are all within the corresponding preset range, then proceed to the next step, otherwise it means that the electrical load of the power supply of the drone fire fighting system is abnormal;
[0034] Match each group of Qm, Um, Wm with q, u, w respectively. If any group of Qm, Um, Wm matches q, u, w, it means that the electrical load of the UAV fire fighting system power supply is normal. Otherwise, it means that the electrical load of the UAV fire fighting system power supply is abnormal.
[0035] As a further solution of the present invention: if the electrical load of the power supply of the drone fire fighting system is abnormal, the duration of the abnormality is counted and marked as T, and T is compared with the preset time t. If T≤t, it means that the load recovery capacity is normal, and if T>t, it means that the load recovery capacity is abnormal.
[0036] As a further solution of the present invention: the specific process of the graded warning is:
[0037] If the analysis results of the environmental analysis model are abnormal, a first-level warning will be issued;
[0038] If the analysis result of the load analysis model is that the electrical load of the UAV firefighting system power supply is abnormal and the load recovery capacity is normal, a second-level warning is issued;
[0039] If the analysis result of the load analysis model is that the electrical load of the UAV fire fighting system power supply is abnormal and the load recovery capacity is abnormal, a third-level warning will be issued.
[0040] As a further solution of the present invention: the issuing of an alarm of a corresponding level is specifically:
[0041] If a level 1 warning occurs, the edge of the display screen on the drone control terminal will flash yellow;
[0042] If a level 2 warning occurs, the edge of the display screen on the drone control terminal will flash red;
[0043] If a level 3 warning appears, the edge of the display screen on the drone control terminal will flash red and yellow alternately.
[0044] Compared with the prior art, the present invention has the following beneficial effects:
[0045] 1. This application first constructs an environmental analysis model, selects representative feature records from previous flight records, and then uses the constructed load analysis model to analyze the electrical load parameters of the UAV fire fighting system power supply in combination with the previously selected feature records, thereby quickly and accurately analyzing whether there are any abnormalities in the electrical load of the UAV fire fighting system power supply, and discovering the abnormalities in time to facilitate the taking of measures. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 The figure is a flow chart of a method for analyzing the electrical load of a power supply of a UAV fire fighting system. DETAILED DESCRIPTION
[0047] 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.
[0048] As mentioned in the background technology of this application, research has found that the existing electrical load analysis method cannot quickly and accurately analyze whether there is an abnormality in the electrical load of the drone fire fighting system power supply, and thus cannot detect the abnormality and take measures in time, which has certain defects.
[0049] In order to solve the above-mentioned defects, the present application discloses a method for analyzing the electrical load of the power supply of a drone fire fighting system, which can quickly and accurately analyze whether there is any abnormality in the electrical load of the power supply of the drone fire fighting system, and detect the abnormality in time to facilitate the taking of measures.
[0050] The following will describe in detail how the solution of the present application solves the above technical problems in conjunction with the accompanying drawings.
[0051] See also Figure 1 In an embodiment of the present invention, a method for analyzing the electrical load of a power supply of a UAV firefighting system includes the following steps: load data collection, i.e., real-time monitoring and collection of the electrical parameters of the UAV firefighting system by using a monitoring device, wherein the electrical parameters include real-time current, voltage and power; environmental data collection, i.e., real-time monitoring and collection of the environmental parameters of the current UAV environment by using sensors, wherein the environmental parameters include the altitude, temperature, humidity, wind direction and wind force of the UAV; load characteristic analysis, firstly, constructing an environmental analysis model, screening out representative characteristic records from previous flight records, then constructing a load analysis model, and outputting the analysis results; and performing graded warnings and issuing corresponding levels of alarms according to the analysis results. This application first constructs an environmental analysis model, screens out representative characteristic records from previous flight records, and then uses the constructed load analysis model to analyze the electrical load parameters of the power supply of the UAV firefighting system in combination with the previously screened characteristic records, thereby quickly and accurately analyzing whether there is an abnormality in the electrical load of the power supply of the UAV firefighting system, and timely discovers the abnormality when it occurs to facilitate taking measures.
[0052] In this embodiment, the specific analysis process of the environmental analysis model is as follows: the collected current wind direction is marked as A1, the current flight direction of the UAV is marked as A2, and the angle between A1 and A2 is marked as α real-time; the angle between each recorded wind direction in the previous flight record and the flight direction of the UAV is marked as αi, i=1···n, where n is a positive integer; the difference between α real-time and αi is calculated, and the absolute value of the difference between α real-time and each αi is counted and marked as ;from The smallest 100 values are selected, and then the flight records corresponding to these 100 values are selected as the initial feature records; based on the initial feature records, secondary screening is performed to obtain the final representative feature records. Different wind directions have different effects on drones. The impact of wind direction on drones is mainly reflected in flight stability, fuel consumption, flight attitude control, and safety. Therefore, the environmental analysis model needs to first select records with similar angles between wind direction and drone flight direction.
[0053] In this embodiment, the specific process of secondary screening based on the initial feature record is: mark the one hundred flight records in the initial feature record as Bj, j=1...100; then extract the altitude, temperature, humidity and wind speed of the drone in this flight record from Bj, and mark the altitude of the drone as Hj, the temperature as Cj, the humidity as Dj, and the wind speed as Ej; based on the altitude Hj, temperature Cj, humidity Dj and wind speed Ej of the drone, generate the radar map Pj corresponding to Bj; mark the current altitude of the drone collected in real time as h, the temperature as Cj, the humidity as Dj, and the wind speed as Ej. The radar map p of the current environment of the drone is generated by marking c, humidity d, and wind force e; compare p with Pj for similarity. If the similarity between p and Pj is greater than 90%, Pj is planned to the first sequence; if the similarity between p and Pj is greater than 80% and less than or equal to 90%, Pj is planned to the second sequence; if the similarity between p and Pj is greater than 70% and less than or equal to 80%, Pj is planned to the third sequence; if the similarity between p and Pj is less than or equal to 70%, Pj is planned to the fourth sequence; mark the number of Pj in the first sequence as F1, and the number of Pj in the second sequence as F2. The number of Pj is marked as F2, the number of Pj in the third sequence is marked as F3, and the number of preset feature records is marked as f; if F1≥f, f flight records Bj corresponding to radar charts Pj are selected from the first sequence as the final representative feature records; if F1<f, proceed to the next step; if (F1+F2)≥f, 2f flight records Bj corresponding to radar charts Pj are selected from the first sequence and the second sequence as the final representative feature records; if the number of radar charts Pj in the first sequence and the second sequence does not reach 2f, select the flight records Bj from the third sequence. If the number of Pj in the third sequence still does not reach 2f, continue to supplement from the fourth sequence; if (F1+F2) <f, proceed to the next step; (F1+F2+F3) ≥f, select 3f flight records Bj corresponding to radar charts Pj from the first sequence, the second sequence and the third sequence as the final representative feature records. If the number of radar charts Pj in the first sequence, the second sequence and the third sequence does not reach 3f, supplement from the fourth sequence; if (F1+F2+F3) <f, it means that the analysis result of this environmental analysis model is abnormal. Environmental factors such as the altitude, temperature, humidity and wind force of the drone have a significant impact on its performance and flight stability. In order to ensure that representative feature records can be screened out, this application generates radar charts through the initial feature records screened out before, and then obtains the final representative feature records through comparative analysis, thereby improving the accuracy of the analysis results of the subsequent load analysis model. It should be noted that the lower the similarity, the worse the representativeness, which requires screening more records to make up for the quality with quantity.
[0054] In this embodiment, when selecting feature records corresponding to radar charts Pj from the first sequence, the second sequence, the third sequence, and the fourth sequence, radar charts with higher similarity rankings in the sequence are preferentially selected. This setting can better select records corresponding to radar charts with high similarity.
[0055] In this embodiment, the specific analysis process of the load analysis model is as follows: the representative feature records analyzed by the environmental analysis model are marked as Gm, m=1···k, where k is a positive integer; the power parameters of the UAV fire fighting system during this flight are extracted from Gm, and the extracted current is marked as Qm, the voltage is marked as Um, and the power is marked as Wm; the current, voltage and power of the UAV fire fighting system monitored in real time are marked as q, u, and w respectively; if q, u, and w are all within the corresponding preset intervals, then the next step is entered, otherwise it indicates that the UAV fire fighting system power supply electrical load is abnormal; each group of Qm, Um, and Wm are matched with q, u, and w respectively, if any group of Qm, Um, and Wm matches q, u, and w, it indicates that the UAV fire fighting system power supply electrical load is normal, otherwise it indicates that the UAV fire fighting system power supply electrical load is abnormal. Through the constructed load analysis model, the UAV fire fighting system power supply electrical load parameters are analyzed in combination with the previously screened feature records, so as to quickly and accurately analyze whether the UAV fire fighting system power supply electrical load is abnormal, and timely discover when an abnormality occurs to facilitate taking measures.
[0056] In this embodiment, if the electrical load of the power supply of the drone fire fighting system is abnormal, the abnormal duration is counted and marked as T, and T is compared with the preset time t. If T≤t, it means that the load recovery capacity is normal, and if T>t, it means that the load recovery capacity is abnormal. This setting can quickly analyze whether there is an abnormality in the load recovery capacity.
[0057] In this embodiment, the specific process of graded warning is as follows: if the analysis result of the environmental analysis model is abnormal, a first-level warning is issued; if the analysis result of the load analysis model is that the electrical load of the power supply of the UAV fire fighting system is abnormal, and the load recovery capacity is normal, a second-level warning is issued; if the analysis result of the load analysis model is that the electrical load of the power supply of the UAV fire fighting system is abnormal, and the load recovery capacity is abnormal, a third-level warning is issued. This setting can issue different levels of warnings according to the analysis results of the environmental analysis model and the load analysis model, thereby making it easier for staff to understand the urgency of the situation.
[0058] In this embodiment, the corresponding level of alarm is issued as follows: if a level 1 warning occurs, the edge of the display screen of the drone control terminal flashes yellow; if a level 2 warning occurs, the edge of the display screen of the drone control terminal flashes red; if a level 3 warning occurs, the edge of the display screen of the drone control terminal flashes red and yellow alternately. This setting can help staff quickly understand the level of the warning.
[0059] The present invention first constructs an environmental analysis model, screens out representative feature records from previous flight records, and then uses the constructed load analysis model to analyze the electrical load parameters of the UAV fire fighting system power supply in combination with the previously screened feature records, thereby quickly and accurately analyzing whether there is any abnormality in the electrical load of the UAV fire fighting system power supply, and discovering the abnormality in time to facilitate the taking of measures.
[0060] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
[0061] What is described above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
Claims
1. A method for analyzing the electrical load of a power supply of a UAV fire fighting system, characterized in that: The following steps are involved: Load data collection, i.e. real-time monitoring and collection of power parameters of the UAV firefighting system by using a monitoring device, where the power parameters include real-time current, voltage and power; Environmental data collection, that is, real-time monitoring and collection of environmental parameters of the current drone environment through sensors, where environmental parameters include the drone's altitude, temperature, humidity, wind direction and wind speed; Load characteristic analysis: first build an environmental analysis model, select representative characteristic records from previous flight records, then build a load analysis model and output the analysis results; Make graded warnings based on the analysis results and issue alarms of corresponding levels; The specific analysis process of the environmental analysis model is as follows: The current wind direction collected is marked as A1, the current flight direction of the drone is marked as A2, and the angle between A1 and A2 is marked as α real-time; The angle between the wind direction and the flight direction of the UAV in each record in the previous flight record is marked as αi, i = 1···n, where n is a positive integer; Calculate the difference between α real-time and αi, count the absolute value of the difference between α real-time and each αi and mark it as ; from Filter out the smallest 100 values, and then filter out the flight records corresponding to these 100 values as initial feature records; Perform secondary screening based on the initial feature records to obtain the final representative feature records; The specific process of secondary screening based on the initial feature record is as follows: The one hundred flight records in the initial feature record are marked as Bj, j = 1···100; Then extract the altitude, temperature, humidity and wind speed of the drone in this flight record from Bj, and mark the altitude of the drone as Hj, the temperature as Cj, the humidity as Dj, and the wind speed as Ej; Generate the radar map Pj corresponding to Bj based on the altitude Hj, temperature Cj, humidity Dj and wind force Ej of the drone; The real-time collected data of the current drone’s altitude is marked as h, the temperature is marked as c, the humidity is marked as d, and the wind speed is marked as e, and a radar map p of the current drone’s environment is generated; Compare p and Pj for similarity. If the similarity between p and Pj is greater than 90%, Pj is planned to the first sequence. If the similarity between p and Pj is greater than 80% and less than or equal to 90%, Pj is planned to the second sequence. If the similarity between p and Pj is greater than 70% and less than or equal to 80%, Pj is planned to the third sequence. If the similarity between p and Pj is less than or equal to 70%, Pj is planned to the fourth sequence. The number of Pj in the first sequence is marked as F1, the number of Pj in the second sequence is marked as F2, the number of Pj in the third sequence is marked as F3, and the number of preset feature records is marked as f; If F1≥f, the flight records Bj corresponding to f radar charts Pj are selected from the first sequence as the final representative feature records. If F1<f, proceed to the next step. If (F1+F2)≥f, select 2f flight records Bj corresponding to radar charts Pj from the first and second sequences as the final representative feature records. If the number of radar charts Pj in the first and second sequences does not reach 2f, supplement them from the third sequence. If the number of Pj in the third sequence still does not reach 2f, continue to supplement from the fourth sequence. If (F1+F2)<f, proceed to the next step. If (F1+F2+F3)≥f, the flight records Bj corresponding to 3f radar charts Pj are selected from the first sequence, the second sequence and the third sequence as the final representative feature records. If the number of radar charts Pj in the first sequence, the second sequence and the third sequence does not reach 3f, they are supplemented from the fourth sequence; if (F1+F2+F3)<f, it means that the analysis result of this environmental analysis model is abnormal.
2. The method for analyzing the electrical load of the power supply of a UAV fire fighting system according to claim 1, characterized in that: When selecting feature records corresponding to the radar chart Pj from the first sequence, the second sequence, the third sequence and the fourth sequence, the radar charts with the highest similarity ranking in the sequence are preferentially selected.
3. The method for analyzing the electrical load of the power supply of the unmanned aerial vehicle fire fighting system according to claim 2 is characterized in that: The specific analysis process of the load analysis model is as follows: The representative feature records analyzed by the environmental analysis model are marked as Gm, m = 1···k, where k is a positive integer; Extract the power parameters of the UAV firefighting system during this flight from Gm, and mark the extracted current as Qm, voltage as Um, and power as Wm; The current, voltage and power of the drone firefighting system monitored in real time are marked as q, u and w respectively; If q, u, and w are all within the corresponding preset range, then proceed to the next step, otherwise it means that the electrical load of the power supply of the drone fire fighting system is abnormal; Match each group of Qm, Um, Wm with q, u, w respectively. If any group of Qm, Um, Wm matches q, u, w, it means that the electrical load of the UAV fire fighting system power supply is normal. Otherwise, it means that the electrical load of the UAV fire fighting system power supply is abnormal.
4. The method for analyzing the electrical load of the power supply of the unmanned aerial vehicle fire fighting system according to claim 3 is characterized in that: If the electrical load of the power supply of the drone fire fighting system is abnormal, the duration of the abnormality is counted and marked as T. T is compared with the preset time t. If T≤t, it means that the load recovery capacity is normal. If T>t, it means that the load recovery capacity is abnormal.
5. A method for analyzing the electrical load of a power supply of a UAV firefighting system according to claim 4, characterized in that: The specific process of the graded warning is as follows: If the analysis results of the environmental analysis model are abnormal, a first-level warning will be issued; If the analysis result of the load analysis model is that the electrical load of the UAV firefighting system power supply is abnormal and the load recovery capacity is normal, a second-level warning is issued; If the analysis result of the load analysis model is that the electrical load of the UAV fire fighting system power supply is abnormal and the load recovery capacity is abnormal, a third-level warning will be issued.
6. A method for analyzing the electrical load of a power supply of a UAV firefighting system according to claim 5, characterized in that: The specific alarms issued at corresponding levels are: If a level 1 warning occurs, the edge of the display screen on the drone control terminal will flash yellow; If a level 2 warning occurs, the edge of the display screen on the drone control terminal will flash red; If a level 3 warning appears, the edge of the display screen on the drone control terminal will flash red and yellow alternately.
