Automatic fire extinguishing control method and device based on power data monitoring

Abstract

The present invention relates to an automatic fire extinguishing control method and device based on power data monitoring, and relates to the technical field of power systems, including: monitoring the electrical parameter sequence, vibration signal sequence, and temperature sequence of power cables through sensors within power facilities; performing contact resistance time-domain fluctuation analysis and power consumption time-domain fluctuation analysis to obtain contact resistance fluctuation factors and power consumption fluctuation factors, and calculating to obtain temperature shock factors; performing fitting verification of the temperature shock factor changes based on the temperature sequence to obtain a verification risk factor; predicting the probability of fire based on the electrical parameter sequence and the temperature sequence, and calculating the fire factor in combination with the verification risk factor, and sending a control signal to control the activation of the fire extinguishing device when the fire factor is greater than a threshold value of the fire factor. The present invention solves the technical problems in the prior art that power facilities cannot be effectively monitored and detected in the early stages of fires, and the effectiveness of power data monitoring and analysis is insufficient, resulting in fire hazards in power facilities.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to an automatic fire extinguishing control method and device based on power data monitoring. Background Art

[0002] During the operation of power facilities, equipment and lines may experience varying degrees of aging, short circuits, overloads, and other issues, which can easily lead to fires. Overload or poor temperature control can cause line temperatures to rise, leading to fires. Without effective control, fires can spread rapidly and eventually become widespread.

[0003] Existing technologies typically monitor voltage and current and implement circuit breakers, such as fuses, for fire protection. However, some fuses fail to blow in time. Consequently, existing technologies suffer from a lack of effective early detection and analysis of power facility fires, resulting in insufficient effectiveness of power data monitoring and analysis, leading to potential fire hazards in power facilities. Summary of the Invention

[0004] The present invention addresses the technical problems in the prior art, such as the inability to effectively monitor and detect the early stages of fires in power facilities, the ineffectiveness of power data monitoring and analysis, and the resulting potential fire hazards in power facilities. An automatic fire extinguishing control method and device based on power data monitoring is proposed.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] In the first aspect, the present invention provides an automatic fire extinguishing control method based on power data monitoring, comprising: monitoring the electrical parameter sequence, vibration signal sequence and temperature sequence of the power cable through electrical sensors, vibration sensors and temperature sensors in the power facility, and transmitting them to the cloud server through the Internet of Things; performing a contact resistance time-domain fluctuation analysis based on the vibration signal sequence to obtain a contact resistance fluctuation factor, performing a power consumption time-domain fluctuation analysis based on the electrical parameter sequence to obtain a power consumption fluctuation factor, and calculating a temperature shock factor in combination with the contact resistance fluctuation factor; performing a change fitting verification of the temperature shock factor based on the temperature sequence to obtain a verification risk factor; performing a fire probability prediction based on the electrical parameter sequence and the temperature sequence, and calculating a fire factor in combination with the verification risk factor, and when the fire factor is greater than a fire factor threshold, sending a control signal to control the start of the fire extinguishing device.

[0007] In the second aspect, the present invention provides an automatic fire extinguishing control device based on power data monitoring, including: an electrical data monitoring module, which is used to monitor the electrical parameter sequence, vibration signal sequence and temperature sequence of the power cable through electrical sensors, vibration sensors and temperature sensors in the power facilities, and transmit them to the cloud server through the Internet of Things; a power shock analysis module, which is used to perform contact resistance time domain fluctuation analysis based on the vibration signal sequence to obtain the contact resistance fluctuation factor, and perform power consumption time domain fluctuation analysis based on the electrical parameter sequence to obtain the power consumption fluctuation factor, and calculate the temperature shock factor in combination with the contact resistance fluctuation factor; a temperature change verification module, which is used to perform change fitting verification of the temperature shock factor based on the temperature sequence to obtain a verification risk factor; a fire prediction control module, which is used to predict the probability of fire based on the electrical parameter sequence and the temperature sequence, and calculate the fire factor in combination with the verification risk factor, and when the fire factor is greater than the fire factor threshold, send a control signal to control the fire extinguishing device to start.

[0008] The beneficial effects of the present invention are as follows: by deploying sensors within the power facilities, the present invention monitors the electrical parameter sequence, vibration signal sequence, and temperature sequence of the power cables in real time, and transmits the data to the cloud server with the help of the Internet of Things, it can realize remote data analysis and automatic control, avoiding the problem of fire out of control caused by delayed response or malfunction of traditional fuse protection. Among them, the monitoring and analysis of the vibration signal sequence can identify the looseness of the cable or connector, and the contact resistance fluctuation factor is calculated by using the contact resistance time domain fluctuation analysis to effectively identify the resistance change caused by poor contact. The power consumption time domain fluctuation analysis extracts the power consumption fluctuation factor through the electrical parameter sequence, and calculates the temperature shock factor in combination with the contact resistance fluctuation factor, accurately reflecting the instantaneous temperature shock phenomenon caused by load fluctuation or poor contact in the power system, and discovering the risk of overload or short-term abnormal high temperature in advance. Furthermore, the temperature shock factor is fitted and verified through the temperature sequence, the number of occurrences of temperature shock is verified, and the verification risk factor is calculated. Finally, the fire probability prediction and fire factor are calculated based on the verification risk factor, electrical parameter sequence, and temperature sequence, thereby improving the prediction accuracy. When the fire factor exceeds the set threshold, a control signal is automatically sent to trigger the fire extinguishing device, realizing intelligent control of the entire process from fire risk identification to fire extinguishing response. It can more accurately predict and respond to fire hazards in power facilities, improve monitoring effectiveness and fire extinguishing timeliness, and avoid the development of fire. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flow chart of an automatic fire extinguishing control method based on power data monitoring provided by the present invention;

[0010] Figure 2 This is a structural schematic diagram of an automatic fire extinguishing control device based on power data monitoring provided by the present invention.

[0011] Reference numerals: electrical data monitoring module 11 , power impact analysis module 12 , temperature change verification module 13 , fire prediction control module 14 . DETAILED DESCRIPTION

[0012] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the specified features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or illustration". Any embodiment of the present invention described as "for example" is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed herein.

[0015] In the technical solution of the present invention, the collection and use of data are carried out with the permission of the user and comply with relevant regulations.

[0016] Example 1, as Figure 1 As shown, an embodiment of the present invention provides an automatic fire extinguishing control method based on power data monitoring, which specifically includes the following steps:

[0017] S10: The electrical parameter sequence, vibration signal sequence and temperature sequence of the power cables are monitored through the electrical sensors, vibration sensors and temperature sensors in the power facilities, and are transmitted to the cloud server through the Internet of Things.

[0018] In the embodiment of the present application, firstly, electrical parameters, vibration signals and temperature during the operation of the power facility are detected by electrical sensors, vibration sensors and temperature sensors arranged in the power facility, and subsequent fire analysis is carried out.

[0019] Among them, the collected electrical parameter sequence, vibration signal sequence and temperature sequence are transmitted to the cloud server through the Internet of Things for subsequent processing. Cloud computing power can provide more accurate processing analysis and realize remote fire extinguishing analysis and control.

[0020] Step S10 in the method provided in the embodiment of the present application includes:

[0021] The electrical parameters, vibration signals and temperature of the cables in the power facilities are monitored at a preset frequency within a recent preset time range through electrical sensors, vibration sensors and temperature sensors in the power facilities;

[0022] According to the monitoring timestamp sequence within the preset time range, the electrical parameters, vibration signals and temperatures are arranged to obtain an electrical parameter sequence, a vibration signal sequence and a temperature sequence, which are transmitted to the cloud server via the Internet of Things.

[0023] In an embodiment of the present application, electrical sensors, vibration sensors, and temperature sensors are first deployed in the power facilities to ensure comprehensive perception and monitoring of the operating status of the cables and their connected components.

[0024] For example, in power facilities such as distribution cabinets, electrical sensors monitor the current and voltage of cables within the facility as electrical parameters. Vibration sensors, such as accelerometers, monitor cable vibration. These sensors, installed on the cables, detect vibration frequency and amplitude when the cables are subjected to external forces (e.g., vibrations from a heavy vehicle passing by) as vibration signals. Temperature sensors, such as thermocouples, monitor the surface temperature of the cable lines.

[0025] Electrical sensors, vibration sensors, and temperature sensors collect data on the target cable's operating status within a preset timeframe at a preset frequency (i.e., a set sampling interval, such as 1 second, 10 seconds, or 1 minute). This data captures electrical parameters, vibration signals, and temperature. For example, the most recent preset timeframe could be the last 10 minutes. A time window mechanism is used to record data within the most recent preset timeframe to ensure data timeliness and integrity while also avoiding waste of storage and computing resources. For example, ten electrical parameters may be collected within the last 10 seconds.

[0026] Furthermore, to ensure data consistency and traceability, each piece of data collected is timestamped to mark the specific time of collection, forming a monitoring timestamp sequence within the most recent preset time range. Following this timestamp sequence, the monitored electrical parameters, vibration signals, and temperatures are arranged in time series, forming a complete electrical parameter sequence, vibration signal sequence, and temperature sequence.

[0027] Electrical parameter sequences can be used to analyze current and voltage fluctuations. Vibration in cables can cause joints to loosen, leading to increased contact resistance. Vibration signal sequences can be used to analyze contact resistance fluctuations. Temperature sequences can be used to track temperature rise trends in cables and equipment.

[0028] After data collection and time series arrangement, the electrical parameter sequence, vibration signal sequence, and temperature sequence are uploaded to the cloud server through the Internet of Things. For example, a gateway device can be installed in the power facility to transmit data and send the monitoring data to the cloud server for processing or receive signals from the cloud server, avoiding local processing that consumes computing power and affects efficiency. The cloud server receives the above data and performs subsequent processing.

[0029] The embodiments of this application monitor multidimensional data to provide basic data support for power facility operational status assessment, fire risk prediction, and automatic fire extinguishing control. Compared with traditional single current and voltage monitoring solutions, this multimodal monitoring method is more real-time, accurate, and predictive, effectively improving the safety and intelligence level of the power system.

[0030] S20: Perform contact resistance time-domain fluctuation analysis based on the vibration signal sequence to obtain a contact resistance fluctuation factor; perform power consumption time-domain fluctuation analysis based on the electrical parameter sequence to obtain a power consumption fluctuation factor; and calculate and obtain a temperature shock factor in combination with the contact resistance fluctuation factor.

[0031] In this embodiment, vibrations in cable lines within power facilities can cause loose joints, which in turn increases and fluctuates contact resistance. When contact resistance increases, the thermal effect of the joint increases, raising the temperature and potentially causing a fire. Therefore, based on the vibration signal sequence, a time-domain analysis of contact resistance fluctuations is performed to obtain a contact resistance fluctuation factor for subsequent fire prediction analysis.

[0032] Furthermore, fluctuations in electrical parameters within power facilities can increase thermal effects and temperature rise, potentially leading to fires. For example, large, instantaneous fluctuations in current and voltage can lead to increased heat generation. Therefore, based on the electrical parameter sequence, we perform a time-domain power consumption fluctuation analysis to obtain the power consumption fluctuation factor.

[0033] Finally, the two dimensions are combined to calculate the temperature shock factor to reflect the degree of temperature fluctuation caused by the vibration and electrical parameter fluctuation of the cable.

[0034] Step S20 in the method provided in the embodiment of the present application includes:

[0035] Extracting an amplitude signal sequence from the vibration signal sequence;

[0036] According to the vibration monitoring data of the power equipment, a set of sample amplitude signal sequences is collected, and the change amplitude of the contact resistance before and after the vibration of different sample amplitude signal sequences is collected, and marked as a set of sample contact resistance fluctuation factors;

[0037] Using the sample amplitude signal sequence set and the sample contact resistance fluctuation factor set as supervised training data and test data, using machine learning, training and testing the contact resistance time domain fluctuation analysis path, and stopping after convergence;

[0038] The amplitude signal sequence is input into the contact resistance time domain fluctuation analysis path, and the contact resistance fluctuation factor is obtained as an output.

[0039] In this embodiment of the present application, to accurately identify contact resistance fluctuations in cable joints within power facilities, the vibration signal sequence is first processed to extract the amplitude signal sequence. Specifically, the mechanical vibration amplitude within the vibration signal can be extracted and processed using an acceleration vibration sensor. For example, the amplitude of a cable joint at a certain moment is 0.08g (g is the unit of gravity acceleration). In this way, the amplitude signal sequence within the vibration signal sequence is extracted.

[0040] Furthermore, after the amplitude signal extraction is completed, a set of sample amplitude signal sequences is collected based on the vibration monitoring data of the power equipment, that is, the sample amplitude signal sequences of the cables monitored and extracted in the same model power facilities at different times. Then, the contact resistance change amplitude before and after vibration is collected according to the different sample amplitude signal sequences. The contact resistance before and after vibration can be measured by a micro-ohmmeter, and the ratio of the contact resistance after vibration to the contact resistance before vibration is calculated as the contact resistance change amplitude, which is then marked as the sample contact resistance fluctuation factor. For example, the contact resistance of a cable joint before and after vibration is 0.02 mΩ, and the contact resistance after vibration is 0.5 mΩ. The resistance change amplitude is 0.5 mΩ / 0.02 mΩ=250%. In this way, a set of sample contact resistance fluctuation factors is collected and marked.

[0041] Furthermore, a set of sample amplitude signal sequences and a set of sample contact resistance fluctuation factors are used as supervised training data and test data, and machine learning is used to train a contact resistance time domain fluctuation analysis path for analyzing contact resistance time domain fluctuation analysis, and the method is tested until it converges.

[0042] For example, a BP neural network is used to construct a contact resistance time-domain fluctuation analysis path. Its specific architecture includes an input layer, an output layer, and a hidden layer. The hidden layer includes two layers, and the activation function is a ReLU activation function. The sample amplitude signal sequence set and the sample contact resistance fluctuation factor set are divided into supervised training data and test data in a ratio of 8:2. During the training process, the sample amplitude signal sequence is input to obtain the output contact resistance fluctuation factor. The mean square error (MSE) loss function is used to calculate the error loss of the corresponding sample contact resistance fluctuation factor, and then the error is back-propagated to update the network weights. Iterative training is performed until the error loss is less than the set threshold, for example, less than 10 −4 , and then test. If the test error loss is also less than the set threshold, the training converges. Otherwise, continue iterative training until convergence.

[0043] The current amplitude signal sequence is input into the trained contact resistance time-domain fluctuation analysis path, and the corresponding contact resistance fluctuation factor is output. The contact resistance fluctuation factor reflects the magnitude of the contact resistance change caused by the loosening of the cable line connector due to vibration.

[0044] The embodiment of the present application can obtain contact resistance changes based on vibration signal monitoring and contact resistance fluctuation analysis, thereby realizing intelligent identification and early warning of poor contact conditions of power equipment, and providing accurate data support for fire protection and equipment operation and maintenance.

[0045] Step S20 in the method provided in the embodiment of the present application further includes:

[0046] Randomly selecting multiple groups of current parameters within the electrical parameter sequence, each group of current parameters including two current parameters;

[0047] Calculating the current fluctuation amplitudes of two current parameters within each set of current parameters as a plurality of electrical fluctuation coefficients;

[0048] Filter the largest electrical fluctuation coefficient as the electricity consumption fluctuation factor.

[0049] In the embodiment of the present application, sudden fluctuations in user power consumption can cause fluctuations in electrical parameters, which can also lead to temperature increases and, in turn, fires in power lines. Therefore, an analysis of recent electrical fluctuations within power facilities is performed based on electrical parameter sequences.

[0050] Specifically, an electrical parameter sequence refers to a data set of current, voltage, power factor, etc. that varies over time. In the embodiment of the present application, electrical fluctuation analysis is performed based on current. Specifically, a current parameter sequence is extracted from the electrical parameter sequence, and then multiple groups of current parameter pairs are randomly selected from the electrical parameter sequence. Each group of data contains current values at two different time points, such as (I1, I2), (I3, I4), ..., (Im, In). For example, five groups of current parameter pairs are randomly selected, and m and n are 9 and 10.

[0051] Furthermore, the current fluctuation amplitudes of the two current parameters within each current parameter group are calculated as multiple electrical fluctuation coefficients. Specifically, the ratio of the larger current parameter to the smaller current parameter is calculated as the electrical fluctuation coefficient. For example, if Im and In are 100A and 75A, respectively, the electrical fluctuation coefficient is 100A / 75A = 133%. In this way, multiple electrical fluctuation coefficients are calculated.

[0052] Furthermore, the largest electrical fluctuation coefficient among the multiple electrical fluctuation coefficients is selected as the power fluctuation factor, which reflects the maximum fluctuation degree of current within a recent preset time range. The larger the power fluctuation factor, the greater the probability of fire.

[0053] In step S20 of the method provided in the embodiment of the present application, the temperature shock factor is calculated by combining the power fluctuation factor and the contact resistance fluctuation factor, as shown in the following formula:

[0054] ;

[0055] in, is the temperature shock factor, and C is the heat dissipation factor, which depends on the heat dissipation capacity of the power facility, ambient temperature, ventilation conditions, etc. For example, when the ventilation environment is good and the ambient temperature is less than 25°C, C is set to 0.6. When the ventilation environment is poor and the ambient temperature is greater than 25°C and less than 35°C, C is set to 1. When the ambient temperature is greater than 35°C, C is set to 1.5. is the electricity consumption fluctuation factor, is the contact resistance fluctuation factor.

[0056] In the embodiment of the present application, in order to accurately evaluate the instantaneous impact of the temperature of the power facility during recent operation, the contact resistance fluctuation factor of the contact resistance fluctuation and the power consumption fluctuation factor of the power current fluctuation are combined to analyze and calculate the temperature shock factor.

[0057] The law of temperature change in power facilities is based on the Joule heating effect, which is expressed as follows:

[0058] Where Q is heat, I is current, R is contact resistance, and t is time. Therefore, the greater the power fluctuation factor, the greater the contact resistance fluctuation factor. That is, the greater the current fluctuation amplitude caused by power fluctuations, and the greater the contact resistance fluctuation due to vibration, the greater the temperature fluctuation of the cables within the power facility. The temperature shock factor reflects the magnitude of the cable temperature change due to fluctuations in the power fluctuation factor and the contact resistance fluctuation factor, and is proportional to the square of the power fluctuation factor and the contact resistance fluctuation factor.

[0059] The embodiment of the present application analyzes the amplitude of current fluctuations and contact resistance fluctuations based on recent electrical parameter sequences and vibration signal sequences, and then calculates the amplitude of future temperature fluctuations, namely the temperature shock factor. Since cable heating has a certain hysteresis, the above steps can predict and calculate the amplitude of future temperature fluctuations caused by the recent electrical parameter sequence and vibration signal sequence, thereby providing a data basis for the subsequent analysis and calculation of the predicted probability of power facility fires. Specifically, the larger the temperature shock factor, the greater the probability of fire.

[0060] S30: performing a fitting verification of the change of the temperature shock factor according to the temperature sequence to obtain a verification risk factor.

[0061] In the embodiment of the present application, the temperature series and the temperature monitoring data of the cables in the power facilities in the historical period are used to perform a fitting verification of the change of the temperature shock factor currently predicted and calculated, wherein the proportion of the temperature shock factor appearing in the cable temperature monitoring in the historical period is specifically analyzed.

[0062] If the temperature shock factor occurs at a high rate, it means that the current predicted cable temperature change has occurred more frequently in the past, which indicates that the temperature is relatively safe, and the probability of fire is low. If the temperature shock factor occurs at a low rate, it means that the current predicted cable temperature change has occurred less frequently in the past, which indicates that the temperature is relatively unsafe, an extreme case, and the probability of fire is high.

[0063] Step S30 in the method provided in the embodiment of the present application includes:

[0064] Retrieve the historical temperature matrix within the historical time and add the temperature sequence;

[0065] In the historical temperature matrix, the number of time windows in which the temperature change amplitude within the preset time window is greater than or equal to the temperature shock factor is extracted, the time length ratio is calculated, and the verification risk factor is obtained by calculation.

[0066] In the embodiment of the present application, in the data record of the cloud server, all temperature sequences of the power cable monitoring transmission in the historical time are retrieved and sorted by time to obtain the historical temperature matrix.

[0067] Then, configure a preset time window, which specifies the duration of cable temperature fluctuations. Because cable temperature changes have a certain hysteresis compared to current changes, a preset time window is set to verify the temperature shock factor. Specifically, calculate the maximum length of time from the beginning of an increase to the end of a cable temperature fluctuation within the power facility over a historical period, and use this as the preset time window. For example, this window is 10 minutes.

[0068] Furthermore, within the historical temperature matrix, the historical temperature matrix is divided according to preset time windows to obtain historical continuous temperature sequences within multiple preset time windows, and then the number of time windows in which the temperature change amplitude within the preset time window is greater than or equal to the temperature shock factor is extracted. For example, the ratio of the maximum temperature to the minimum temperature in the historical continuous temperature sequence within each preset time window is calculated, and then it is determined whether it is greater than or equal to the temperature shock factor. If so, it is recorded as a time window in which the temperature change amplitude is greater than or equal to the temperature shock factor. In this way, the number of time windows is obtained by discriminant statistics.

[0069] Furthermore, the ratio of this number of time windows to the total number of pre-set time windows within the historical temperature matrix is calculated as the time length ratio. This is then subtracted from 1 to obtain the verification risk factor. Specifically, the fewer times the predicted cable temperature change amplitude (temperature shock factor) occurs within the historical timeframe, the more extreme the current temperature change amplitude is, the greater the risk, and the larger the verification risk factor. For example, if the time length ratio is 3%, the verification risk factor is 1-3% = 97%.

[0070] If the temperature shock factor has a high occurrence rate in the historical temperature matrix, that is, the verification risk factor is small, then the amplitude of the cable temperature change currently predicted and calculated has occurred frequently in the historical period, which is relatively safe, and the probability of fire is low. If the temperature shock factor has a low occurrence rate in the historical temperature matrix, that is, the verification risk factor is large, then the amplitude of the cable temperature change currently predicted and calculated has occurred rarely in the historical period, which is relatively unsafe, an extreme case, and a high probability of fire.

[0071] By retrieving and verifying the temperature shock factor in the historical data of power facilities, obtaining the time proportion of its occurrence in temperature fluctuation changes in historical time, and calculating and verifying the risk factor, the risk level and fire probability of the current predicted and calculated temperature shock factor can be reflected. By introducing power consumption fluctuations, contact resistance fluctuations and temperature shock fluctuation verification, the accuracy and reliability of power facility fire prediction analysis can be improved.

[0072] S40: Predicting the probability of fire based on the electrical parameter sequence and the temperature sequence, and calculating the fire factor in combination with the verification risk factor. When the fire factor is greater than a fire factor threshold, sending a control signal to start the fire extinguishing device.

[0073] In this embodiment, machine learning is used to predict fire probability based on electrical parameter and temperature sequences. Combined with the verified risk factor calculated using the temperature fluctuation analysis described above, a comprehensive fire factor is calculated to reflect the probability of fire in power facilities. This factor then determines whether automatic fire extinguishing should be initiated. Specifically, the fire factor is determined to be greater than a fire factor threshold. If so, a control signal is sent to activate the fire extinguishing device. Otherwise, no action is taken and monitoring continues.

[0074] Step S40 in the method provided in the embodiment of the present application includes:

[0075] Train a fire probability predictor;

[0076] Inputting the electrical parameter sequence and the temperature sequence into a fire probability predictor to predict the fire probability;

[0077] According to the fire probability and the verification risk factor, the fire factor is calculated and determined to be greater than the fire factor threshold. If so, a control signal is sent to start the fire extinguishing device; if not, no processing is performed.

[0078] In this embodiment, machine learning is first used to train a fire probability predictor based on two dimensional data sets: electrical parameter sequences and temperature sequences. Electrical changes and sharp temperature increases can cause cable fires, and the greater the electrical change and the greater the temperature increase, the greater the probability of cable fire. Therefore, fire probability can be predicted based on electrical parameter sequences and temperature sequences.

[0079] Training a fire probability predictor involves:

[0080] Based on the fire monitoring data of similar power facilities, a set of sample electrical parameter sequences and a set of sample temperature sequences are collected, and the proportion of fires under different sample electrical parameter sequences and sample temperature sequences are collected and marked as a sample fire probability set;

[0081] The sample electrical parameter sequence set, the sample temperature sequence set, and the sample fire probability set are used to train and test a fire probability predictor until convergence.

[0082] In this embodiment, based on fire monitoring data from similar power facilities, sample electrical parameter sequences and sample temperature sequences are collected to obtain a set of sample electrical parameter sequences and a set of sample temperature sequences. The proportion of fire events occurring under different sample electrical parameter sequences and sample temperature sequences is then collected and labeled as a set of sample fire probabilities. For example, the fire probability is 1%.

[0083] Among them, the number of fires occurring in power facilities under multiple sample electrical parameter sequences and sample temperature sequences with the same average electrical parameters (such as average current) and average temperature can be calculated, and then the ratio to the number of multiple sample electrical parameter sequences and sample temperature sequences with the same average electrical parameters (such as average current) and average temperature can be calculated as the probability of fire.

[0084] In the embodiment of the present application, the sample electrical parameter sequence set, the sample temperature sequence set and the sample fire probability set are continued to be used to train and test the fire probability predictor. For example, a BP neural network is used to construct a fire probability predictor, and its specific architecture includes an input layer, an output layer and a hidden layer. The hidden layer includes three layers, and the activation function is a ReLU activation function. The input features of the input layer are the sample electrical parameter sequence and the sample temperature sequence, and the output features of the output layer are the sample fire probability. The sample electrical parameter sequence set, the sample temperature sequence set and the sample fire probability set are divided into supervised training data and test data in a ratio of 8:2. During the training process, the sample electrical parameter sequence and the sample temperature sequence are input to obtain the output fire probability. The mean square error (MSE) loss function is used to calculate the error loss with the corresponding sample fire probability, and then the error is back-propagated to update the network weights. The iterative training is performed in this way until the error loss is less than the set threshold, for example, less than 10 −4 , and then test. If the test error loss is also less than the set threshold, the training converges. Otherwise, continue iterative training until convergence.

[0085] Based on the trained fire probability predictor, the currently collected electrical parameter sequence and temperature sequence are input into the fire probability predictor, and the fire probability is obtained by prediction output.

[0086] Furthermore, based on the previously calculated verification risk factor and combined with the fire probability, a comprehensive parameter reflecting the fire risk probability is calculated based on these two dimensions, namely the fire factor. For example, the average of the fire probability and the verification risk factor is calculated as the fire factor. For example, if the fire probability is 1% and the verification risk factor is 3%, the fire factor is (1% + 3%) / 2 = 2%.

[0087] Furthermore, it is determined whether the fire factor is greater than the fire factor threshold. If so, the risk of fire in the power facility cable is extremely high, and automatic fire extinguishing is required to avoid the fire from developing due to undetected fire extinguishing. Fire extinguishing should be carried out at an early stage. Otherwise, no processing is performed and monitoring continues. The fire factor threshold can be obtained by using the method described above to process the electrical parameter sequence, vibration signal sequence, and temperature sequence obtained from monitoring multiple similar power facilities before the fire, and then calculating the average value to set the fire factor. For example, the fire factor threshold is 85%.

[0088] If the ignition factor exceeds the ignition factor threshold, the cloud server can send a control signal through the Internet of Things to control the fire extinguishing device in the power facility to activate the fire extinguishing device, such as an aerosol fire extinguishing device. The control signal can be a thermal line, which controls the thermal line through the circuit to first burn the explosive column in the aerosol fire extinguishing device, and then start to spray the aerosol to extinguish the fire.

[0089] By integrating the verified risk factors and the predicted fire probability to calculate the fire factor, and fusing the two dimensions to obtain the fire risk probability parameters, the accuracy and reliability of fire prediction can be improved, thereby improving the stability of fire extinguishing control and the safety of power facilities.

[0090] The embodiment of the present invention provides an automatic fire extinguishing control method based on power data monitoring, which has at least the following technical effects:

[0091] By deploying sensors within power facilities, the present invention monitors the electrical parameter sequences, vibration signal sequences, and temperature sequences of power cables in real time. This data is then transmitted to a cloud server via the Internet of Things (IoT). This enables remote data analysis and automated control, avoiding fire uncontrollability issues caused by delayed or malfunctioning traditional fuse protection. Monitoring and analyzing the vibration signal sequence can identify loose cables or connectors. Time-domain fluctuation analysis of contact resistance is used to calculate the contact resistance fluctuation factor, effectively identifying resistance changes caused by poor contact. Time-domain fluctuation analysis of power consumption extracts the power consumption fluctuation factor from the electrical parameter sequence and combines it with the contact resistance fluctuation factor to calculate the temperature shock factor. This accurately reflects transient temperature shocks within the power system caused by load fluctuations or poor contact, enabling early detection of overload or short-term abnormally high temperature risks. Furthermore, the temperature shock factor is fitted and verified using the temperature sequence to verify the number of temperature shocks and calculate a verification risk factor. Finally, the verification risk factor, electrical parameter sequence, and temperature sequence are used to predict fire probability and calculate the fire factor, improving prediction accuracy. When the fire factor exceeds the set threshold, a control signal is automatically sent to trigger the fire extinguishing device, realizing intelligent control of the entire process from fire risk identification to fire extinguishing response. It can more accurately predict and respond to fire hazards in power facilities, improve monitoring effectiveness and fire extinguishing timeliness, and avoid the development of fire.

[0092] Example 2, as Figure 2 As shown, the invention concept is the same as that of the automatic fire extinguishing control method based on power data monitoring in Example 1. This embodiment of the present invention further provides an automatic fire extinguishing control device based on power data monitoring. The explanation of the automatic fire extinguishing control method based on power data monitoring in Example 1 is also applicable to the automatic fire extinguishing control device based on power data monitoring, which includes:

[0093] The electrical data monitoring module 11 is used to monitor the electrical parameter sequence, vibration signal sequence and temperature sequence of the power cable through electrical sensors, vibration sensors and temperature sensors in the power facility, and transmit the data to the cloud server through the Internet of Things;

[0094] The power shock analysis module 12 is configured to perform a contact resistance time-domain fluctuation analysis based on the vibration signal sequence to obtain a contact resistance fluctuation factor, perform a power consumption time-domain fluctuation analysis based on the electrical parameter sequence to obtain a power consumption fluctuation factor, and calculate a temperature shock factor in combination with the contact resistance fluctuation factor;

[0095] The temperature change verification module 13 is used to perform a change fitting verification of the temperature shock factor according to the temperature sequence to obtain a verification risk factor;

[0096] The fire prediction control module 14 is used to predict the fire probability based on the electrical parameter sequence and the temperature sequence, calculate the fire factor in combination with the verification risk factor, and send a control signal to control the activation of the fire extinguishing device when the fire factor is greater than the fire factor threshold.

[0097] Furthermore, the electrical data monitoring module 11 is also used to:

[0098] The electrical parameters, vibration signals and temperature of the cables in the power facilities are monitored at a preset frequency within a recent preset time range through electrical sensors, vibration sensors and temperature sensors in the power facilities;

[0099] According to the monitoring timestamp sequence within the preset time range, the electrical parameters, vibration signals and temperatures are arranged to obtain an electrical parameter sequence, a vibration signal sequence and a temperature sequence, which are transmitted to the cloud server via the Internet of Things.

[0100] Furthermore, the power impact analysis module 12 is also used to:

[0101] Extracting an amplitude signal sequence from the vibration signal sequence;

[0102] According to the vibration monitoring data of the power equipment, a set of sample amplitude signal sequences is collected, and the change amplitude of the contact resistance before and after the vibration of different sample amplitude signal sequences is collected, and marked as a set of sample contact resistance fluctuation factors;

[0103] Using the sample amplitude signal sequence set and the sample contact resistance fluctuation factor set as supervised training data and test data, using machine learning, training and testing the contact resistance time domain fluctuation analysis path, and stopping after convergence;

[0104] The amplitude signal sequence is input into the contact resistance time domain fluctuation analysis path, and the contact resistance fluctuation factor is obtained as an output.

[0105] Furthermore, the power impact analysis module 12 is also used to:

[0106] Randomly selecting multiple groups of current parameters within the electrical parameter sequence, each group of current parameters including two current parameters;

[0107] Calculating the current fluctuation amplitudes of two current parameters within each set of current parameters as a plurality of electrical fluctuation coefficients;

[0108] Filter the largest electrical fluctuation coefficient as the electricity consumption fluctuation factor.

[0109] Furthermore, the power impact analysis module 12 is also used to:

[0110] Combined with the contact resistance fluctuation factor, the temperature shock factor is calculated as follows:

[0111] ;

[0112] in, is the temperature shock factor, C is the heat dissipation factor, is the electricity consumption fluctuation factor, is the contact resistance fluctuation factor.

[0113] Furthermore, the temperature change verification module 13 is further used to:

[0114] Retrieve the historical temperature matrix within the historical time and add the temperature sequence;

[0115] In the historical temperature matrix, the number of time windows in which the temperature change amplitude within the preset time window is greater than or equal to the temperature shock factor is extracted, the time length ratio is calculated, and the verification risk factor is obtained by calculation.

[0116] Furthermore, the fire prediction control module 14 is further configured to:

[0117] Train a fire probability predictor;

[0118] Inputting the electrical parameter sequence and the temperature sequence into a fire probability predictor to predict the fire probability;

[0119] According to the fire probability and the verification risk factor, the fire factor is calculated and determined to be greater than the fire factor threshold. If so, a control signal is sent to start the fire extinguishing device; if not, no processing is performed.

[0120] Among them, training the fire probability predictor includes:

[0121] Based on the fire monitoring data of similar power facilities, a set of sample electrical parameter sequences and a set of sample temperature sequences are collected, and the proportion of fires under different sample electrical parameter sequences and sample temperature sequences are collected and marked as a sample fire probability set;

[0122] The sample electrical parameter sequence set, the sample temperature sequence set, and the sample fire probability set are used to train and test a fire probability predictor until convergence.

[0123] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0124] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The present invention is described with reference to flow diagrams and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flow diagram and / or block diagram, as well as combinations of flows and / or blocks in the flow diagram and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the flow diagram and / or block diagram. Figure 1 flow or flows and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device that implements the flow Figure 1 flow or flows and / or boxes Figure 1 The function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process in the flow. Figure 1 flow or flows and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0128] Although preferred embodiments of the present invention have been described, additional changes and modifications to these embodiments may occur to those skilled in the art once the basic inventive concepts become known.

[0129] 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 present invention and its equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An automatic fire extinguishing control method based on power data monitoring, characterized in that: The method comprises: The electrical parameters, vibration signals and temperature of power cables are monitored through electrical sensors, vibration sensors and temperature sensors in power facilities, and transmitted to the cloud server through the Internet of Things. According to the vibration signal sequence, a contact resistance time domain fluctuation analysis is performed to obtain a contact resistance fluctuation factor. According to the electrical parameter sequence, a power consumption time domain fluctuation analysis is performed to obtain a power consumption fluctuation factor. Combined with the contact resistance fluctuation factor, the temperature shock factor is calculated as follows: ； in, is the temperature shock factor, C is the heat dissipation factor, is the electricity consumption fluctuation factor, is the contact resistance fluctuation factor; According to the temperature sequence, the change fitting verification of the temperature shock factor is performed to obtain the verification risk factor, including: Retrieve the historical temperature matrix within the historical time and add the temperature sequence; In the historical temperature matrix, the number of time windows in which the temperature change amplitude within the preset time window is greater than or equal to the temperature shock factor is extracted, the time length ratio is calculated, and the verification risk factor is calculated, wherein the ratio of the number of time windows to the total number of preset time windows divided in the historical temperature matrix is calculated as the time length ratio, and the verification risk factor is obtained by subtracting the time length ratio from 1; The fire probability is predicted based on the electrical parameter sequence and the temperature sequence, and the fire factor is calculated in combination with the verification risk factor. When the fire factor is greater than the fire factor threshold, a control signal is sent to control the fire extinguishing device to start.

2. The automatic fire extinguishing control method based on power data monitoring according to claim 1 is characterized in that: The electrical parameters, vibration signals, and temperature of power cables are monitored through electrical sensors, vibration sensors, and temperature sensors within power facilities, and transmitted to the cloud server via the Internet of Things, including: The electrical parameters, vibration signals and temperature of the cables in the power facilities are monitored at a preset frequency within a recent preset time range through electrical sensors, vibration sensors and temperature sensors in the power facilities; According to the monitoring timestamp sequence within the preset time range, the electrical parameters, vibration signals and temperatures are arranged to obtain an electrical parameter sequence, a vibration signal sequence and a temperature sequence, which are transmitted to the cloud server via the Internet of Things.

3. The automatic fire extinguishing control method based on power data monitoring according to claim 1 is characterized in that: According to the vibration signal sequence, a contact resistance time domain fluctuation analysis is performed to obtain a contact resistance fluctuation factor, including: Extracting an amplitude signal sequence from the vibration signal sequence; According to the vibration monitoring data of the power equipment, a set of sample amplitude signal sequences is collected, and the change amplitude of the contact resistance before and after the vibration of different sample amplitude signal sequences is collected, and marked as a set of sample contact resistance fluctuation factors; Using the sample amplitude signal sequence set and the sample contact resistance fluctuation factor set as supervised training data and test data, using machine learning, training and testing the contact resistance time domain fluctuation analysis path, and stopping after convergence; The amplitude signal sequence is input into the contact resistance time domain fluctuation analysis path, and the contact resistance fluctuation factor is obtained as an output.

4. The automatic fire extinguishing control method based on power data monitoring according to claim 1 is characterized in that: Based on the electrical parameter sequence, a time-domain power consumption fluctuation analysis is performed to obtain a power consumption fluctuation factor, including: Randomly selecting multiple groups of current parameters within the electrical parameter sequence, each group of current parameters including two current parameters; Calculating the current fluctuation amplitudes of two current parameters within each set of current parameters as a plurality of electrical fluctuation coefficients; Filter the largest electrical fluctuation coefficient as the electricity consumption fluctuation factor.

5. The automatic fire extinguishing control method based on power data monitoring according to claim 1 is characterized in that: According to the verification risk factor, a fire probability prediction is performed according to the electrical parameter sequence and the temperature sequence to obtain the fire probability, including: Train a fire probability predictor; Inputting the electrical parameter sequence and the temperature sequence into a fire probability predictor to predict the fire probability; According to the fire probability and the verification risk factor, the fire factor is calculated and determined to be greater than the fire factor threshold. If so, a control signal is sent to start the fire extinguishing device; if not, no processing is performed.

6. The automatic fire extinguishing control method based on power data monitoring according to claim 5 is characterized in that: Train a fire probability predictor, including: Based on the fire monitoring data of similar power facilities, a set of sample electrical parameter sequences and a set of sample temperature sequences are collected, and the proportion of fires under different sample electrical parameter sequences and sample temperature sequences are collected and marked as a sample fire probability set; The sample electrical parameter sequence set, the sample temperature sequence set, and the sample fire probability set are used to train and test a fire probability predictor until convergence.

7. An automatic fire extinguishing control device based on power data monitoring, characterized in that: The device is used to perform the method according to any one of claims 1 to 6, and the device comprises: The electrical data monitoring module is used to monitor the electrical parameter sequence, vibration signal sequence and temperature sequence of the power cables through electrical sensors, vibration sensors and temperature sensors in the power facilities, and transmit them to the cloud server through the Internet of Things; a power shock analysis module configured to perform a contact resistance time-domain fluctuation analysis based on the vibration signal sequence to obtain a contact resistance fluctuation factor, perform a power consumption time-domain fluctuation analysis based on the electrical parameter sequence to obtain a power consumption fluctuation factor, and calculate a temperature shock factor in combination with the contact resistance fluctuation factor; A temperature change verification module is used to perform a change fitting verification of the temperature shock factor according to the temperature sequence to obtain a verification risk factor; The fire prediction control module is used to predict the fire probability based on the electrical parameter sequence and the temperature sequence, calculate the fire factor in combination with the verification risk factor, and send a control signal to control the activation of the fire extinguishing device when the fire factor is greater than the fire factor threshold.

Images