Electrical fire monitoring and predicting method and device

Abstract

The invention relates to the technical field of fire monitoring, and particularly discloses an electrical fire monitoring and predicting method and device.The electrical fire monitoring and predicting method comprises the following steps that temperature parameters, pyrolysis particle concentration parameters and air quality parameters of a monitored object in multiple calculation periods are obtained; according to each parameter in the plurality of calculation periods, calculating a change trend and a danger coefficient of each parameter; and based on the calculated change trend of each parameter and the danger coefficient, predicting whether a fire occurs at the monitored object. The accuracy of fire prediction can be improved, and the false alarm rate is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of fire monitoring, and in particular to an electrical fire monitoring and prediction method and device. Background Art

[0002] At present, most of the existing electrical fire monitoring solutions generally use residual current electrical fire monitoring detectors, temperature measurement monitoring detectors, fault arc detectors, pyrolysis particle monitoring detectors and other equipment. The data detected by various detectors are diverse and have different functions. Existing electrical fire monitoring equipment often only monitors a certain parameter, which is easily affected by some external factors (such as environmental factors and human factors) and leads to false alarms, which will cause unnecessary waste of manpower and material resources. Summary of the invention

[0003] The present invention provides an electrical fire monitoring and prediction method and device, which can improve the accuracy of fire prediction and reduce the false alarm rate.

[0004] To solve the above problems, the present invention adopts the following technical solutions:

[0005] According to a first aspect of the present invention, an embodiment of the present invention provides an electrical fire monitoring and prediction method, comprising the following steps:

[0006] Obtaining temperature parameters, pyrolysis particle concentration parameters and air quality parameters of the monitored object in multiple calculation cycles;

[0007] According to various parameters in multiple calculation cycles, calculate the change trend and risk factor of each parameter;

[0008] Based on the calculated change trends and risk factors of various parameters, it is predicted whether a fire will occur at the monitored object.

[0009] In some embodiments, the step of predicting whether a fire has occurred at the monitored object based on the calculated change trends and risk factors of the various parameters specifically includes: when the change trend of any parameter is gradually increasing and the ratio of the risk factor to the standard threshold is greater than the set value, it is determined that a fire has occurred at the monitored object; or, when the change trend of any parameter is relatively constant and the risk factor is greater than the standard threshold, it is determined that a fire has occurred at the monitored object.

[0010] In some embodiments, the step of calculating the change trend of each parameter specifically includes: first calculating the overall trend f(t) of each parameter,

[0011]

[0012] In which, each parameter has 2n sampling data points in a calculation cycle, n≥2; t is the time at the end of a calculation cycle; Sa(i) is the real-time value of each parameter at the sampling time;

[0013] Then calculate the subsequent trend g(t) of each parameter based on the 1 / 4 segment data at the end of the calculation cycle.

[0014]

[0015] make g(t)=G={def}, then multiply the matrix F and G to get the changing trend of each parameter Among them, the 9 results of F*G represent 9 changing trends of parameters, H1 is a gradual increase trend, H2 is a gradual increase and then stable trend, H3 is a gradual increase, then maintain, and finally a gradual decrease trend, H4 is a periodic change trend, H5 is a relatively constant trend, H6 is a short-term increase and then return to the initial state trend, H7, H8 and H9 are all load reduction trends.

[0016] In some embodiments, the step of calculating the risk factor specifically includes: the risk factor K is calculated as follows:

[0017]

[0018] Wherein, i is any sampling moment or multiple consecutive sampling moments within a calculation cycle; when i is any sampling moment within a calculation cycle, PMx(i) is the PM value at the i sampling moment, and T(i) is the temperature value at the i sampling moment; when i is multiple consecutive sampling moments within a calculation cycle, PMx(i) and T(i) are both the average values ​​of the multiple consecutive sampling moments.

[0019] In some embodiments, the following steps are also included: after determining that a fire has occurred at the monitored object, determining the danger level of the fire, and issuing a corresponding fire alarm according to the danger level of the fire.

[0020] According to a second aspect of the present invention, an embodiment of the present invention provides an electrical fire monitoring and prediction device, comprising:

[0021] A parameter acquisition module is used to obtain temperature parameters, pyrolysis particle concentration parameters and air quality parameters of the monitored object in multiple calculation cycles;

[0022] A comprehensive calculation module is used to calculate the change trend and risk factor of each parameter based on the parameters in multiple calculation cycles;

[0023] The fire prediction module is used to predict whether a fire will occur at the monitored object based on the calculated change trends and risk factors of various parameters.

[0024] In some embodiments, when the change trend of any parameter is gradually increasing and the ratio of the risk factor to the standard threshold is greater than the set value, the fire prediction module determines that a fire has occurred at the monitored object; or, when the change trend of any parameter is relatively constant and the risk factor is greater than the standard threshold, the fire prediction module determines that a fire has occurred at the monitored object.

[0025] In some embodiments, the comprehensive calculation module calculates the change trend of each parameter according to the following method: first calculate the overall trend f(t) of each parameter,

[0026]

[0027] In which, each parameter has 2n sampling data points in a calculation cycle, n≥2; t is the time at the end of a calculation cycle; Sa(i) is the real-time value of each parameter at the sampling time;

[0028] Then calculate the subsequent trend g(t) of each parameter based on the 1 / 4 segment data at the end of the calculation cycle.

[0029]

[0030] make g(t)=G={def}, then multiply the matrix F and G to get the changing trend of each parameter Among them, the 9 results of F*G represent 9 changing trends of parameters, H1 is a gradual increase trend, H2 is a gradual increase and then stable trend, H3 is a gradual increase, then maintain, and finally a gradual decrease trend, H4 is a periodic change trend, H5 is a relatively constant trend, H6 is a short-term increase and then return to the initial state trend, H7, H8 and H9 are all load reduction trends.

[0031] In some embodiments, the comprehensive calculation module calculates the risk factor according to the following method: The risk factor K is calculated as follows:

[0032]

[0033] Wherein, i is any sampling moment or multiple consecutive sampling moments within a calculation cycle; when i is any sampling moment within a calculation cycle, PMx(i) is the PM value at the i sampling moment, and T(i) is the temperature value at the i sampling moment; when i is multiple consecutive sampling moments within a calculation cycle, PMx(i) and T(i) are both the average values ​​of the multiple consecutive sampling moments.

[0034] In some embodiments, a fire alarm module is also included, which is used to determine the danger level of the fire after determining that a fire has occurred at the monitored object, and to issue a corresponding fire alarm according to the danger level of the fire.

[0035] The present invention has at least the following beneficial effects: the present invention obtains the temperature parameters, pyrolysis particle concentration parameters and air quality parameters of the monitored object within multiple calculation cycles, and then calculates the change trend and hazard factor of each parameter according to the various parameters within the multiple calculation cycles, and finally predicts whether a fire occurs at the monitored object based on the calculated change trend and hazard factor of each parameter. Since multiple parameters are used and the change trend and hazard factor of the comprehensive reference parameters are taken into account, the interference of external factors can be greatly reduced, thereby improving the accuracy of fire prediction and reducing the false alarm rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of the structure of an electrical fire monitoring system according to an embodiment of the present invention;

[0037] Figure 2 A schematic diagram of a flow chart of an electrical fire monitoring and prediction method according to an embodiment of the present invention;

[0038] Figure 3 Schematic diagram of nine changing trends of the present invention;

[0039] Figure 4 A schematic diagram of a module of an electrical fire monitoring and prediction device according to an embodiment of the present invention;

[0040] Figure 5 A schematic diagram of a module of an electrical fire monitoring and prediction device according to another embodiment of the present invention.

[0041] Wherein, the accompanying drawings are marked as follows:

[0042] Temperature detection module 11, pyrolysis particle detection module 12, air quality detection module 13, main control module 20, power module 21, linkage control output module 22;

[0043] Parameter acquisition module 100, comprehensive calculation module 200, fire prediction module 300, fire alarm module 400. DETAILED DESCRIPTION

[0044] The present invention provides the following description with reference to the accompanying drawings to assist in a comprehensive understanding of various embodiments of the present invention as defined by the claims and their equivalents. The description includes various specific details to assist in understanding, but these details should be considered as exemplary only. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the various embodiments described herein without departing from the scope and spirit of the present invention.

[0045] In the description of the present invention, descriptions of orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the drawings and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0046] It will be understood that when one element (eg, a first element) is “connected” to another element (eg, a second element), the element may be directly connected to the other element or an intervening element (eg, a third element) may be present between the element and the other element.

[0047] Before describing the method of the present invention in detail, it is necessary to describe the hardware structure of the electrical fire monitoring and prediction system of the present invention. Figure 1 As shown, the electrical fire monitoring and prediction system includes a temperature detection module 11, a pyrolysis particle detection module 12, an air quality detection module 13, a main control module 20 and a power module 21. The temperature detection module 11, the pyrolysis particle detection module 12, the air quality detection module 13 and the power module 21 are all connected to the main control module 20.

[0048] The power supply module 21 provides power to the main control module 20 and other modules that require power so that these modules can be powered on and work. The temperature detection module 11 includes a temperature sensor, which is fixed on the surface, inside or near the monitored object to detect the temperature in real time or regularly, and send the detected temperature value to the main control module 20. The pyrolytic particle detection module 12 is used to detect the concentration of pyrolytic particles in the environment of the monitored object, and send the detected pyrolytic particle concentration to the main control module 20. The air quality detection module 13 is used to detect the concentration of specific gases (such as hydrogen, toluene, etc.) in the air and / or PM values ​​and other parameters that characterize the air quality in real time or regularly, and send the detected concentration of specific gases and / or PM values ​​to the main control module 20. The main control module 20 may include a control chip such as a single-chip microcomputer, which is used to calculate and process the various parameters obtained according to a set control program, and predict whether a fire occurs.

[0049] Of course, the electrical fire monitoring and prediction system of the present invention may also include a linkage control output module 22 connected to the main control module 20. When the main control module 20 predicts that a fire will occur, it will also inform the linkage control output module 22, and the linkage control output module 22 will distribute the message to the host, server or alarm device.

[0050] The embodiment of the present invention provides an electrical fire monitoring and prediction method, which will be described from the perspective of the main control module. Figure 2 As shown, the following steps are included:

[0051] S100: Acquire temperature parameters, pyrolysis particle concentration parameters and air quality parameters of the monitored object in multiple calculation cycles.

[0052] The duration of each calculation cycle is set in advance. Each calculation cycle has multiple sampling moments. Temperature parameters, pyrolysis particle concentration parameters and air quality parameters are sampled at each sampling moment, so that data of multiple calculation cycles can be obtained. Each calculation cycle has multiple temperature parameters, pyrolysis particle concentration parameters and air quality parameters.

[0053] S200: Calculate the change trend and risk factor of each parameter according to each parameter in a plurality of calculation cycles.

[0054] Since the occurrence of fire will inevitably lead to changes in temperature parameters, pyrolysis particle concentration parameters and air quality parameters, the changing trends of temperature parameters, pyrolysis particle concentration parameters and air quality parameters will indicate whether a fire will occur. Therefore, the changing trends of these parameters are very important, and the hazard factor is a reflection of whether these changing trends are dangerous.

[0055] S300: Predict whether a fire occurs at the monitored object based on the calculated change trends of various parameters and the risk factor.

[0056] By comprehensively judging the changing trends and risk factors of various parameters, it is possible to predict whether a fire has occurred at the monitored object. Therefore, this embodiment uses a variety of parameters that can characterize the fire situation, rather than a single parameter, and comprehensively refers to the changing trends and risk factors of the parameters, which can greatly reduce the interference of external factors, thereby improving the accuracy of fire prediction and reducing the false alarm rate.

[0057] In some embodiments, step S300 specifically includes: when the change trend of any parameter is gradually increasing and the ratio of the risk factor to the standard threshold is greater than the set value, it is determined that a fire has occurred at the monitored object; or, when the change trend of any parameter is relatively constant and the risk factor is greater than the standard threshold, it is determined that a fire has occurred at the monitored object.

[0058] When the trend of the parameter change is gradually increasing, it means that the possibility of fire is very high. In order to avoid misjudgment, it is further judged by the ratio of the hazard coefficient to the standard threshold. The standard threshold and the set value can be pre-set according to historical data or experience. If the ratio of the hazard coefficient to the standard threshold is greater than the set value, it is determined that a fire has occurred at the monitored object. If the ratio of the hazard coefficient to the standard threshold is less than or equal to the set value, it is determined that no fire has occurred at the monitored object. The preset value is less than 1. Since the possibility of fire is already very high, it is not necessary for the hazard coefficient to be equal to or greater than the standard threshold. For example, the preset value can be 0.8.

[0059] When the parameter change trend is relatively constant, that is, the change in the parameter value is very small, it means that the monitored object may be in normal working condition without abnormality, or it may be in the stable period of fire, and the parameter value also changes very little. At this time, the risk factor is needed for further evaluation. If the risk factor is greater than the standard threshold, it is determined that a fire has occurred at the monitored object. If the risk factor is less than or equal to the standard threshold, it is determined that no fire has occurred at the monitored object.

[0060] Except for the above two situations, it is generally believed that no fire has occurred at the monitored object in other situations.

[0061] Furthermore, the step of calculating the change trend of each parameter in step S200 specifically includes: first calculating the overall trend f(t) of each parameter, where the overall trend is the overall embodiment of the parameter change in a calculation cycle. Specifically, it is calculated by the following formula:

[0062]

[0063] In which, each parameter has 2n sampling data points in a calculation cycle, n≥2; t is the time at the end of a calculation cycle; Sa(i) is the real-time value of each parameter at the sampling time;

[0064] Then calculate the subsequent trend g(t) of each parameter based on the 1 / 4 segment data at the end of the calculation cycle.

[0065]

[0066] make g(t)=G={def}, then multiply the matrix F and G to get the changing trend of each parameter Among them, the 9 results of F*G represent 9 changing trends of parameters.

[0067] like Figure 3 As shown, H1 is a gradual growth trend. The temperature, pyrolysis particle concentration and harmful gas content suddenly and sharply increase from the lower normal values, indicating that there is a greater possibility of fire at the monitored object. For this situation, a comprehensive analysis is performed in combination with the hazard coefficient value. If the ratio of the hazard coefficient to the standard threshold is greater than the set value, it is determined that a fire has occurred at the monitored object.

[0068] H2 first increases gradually and then maintains a stable trend. It may be that the line load is operating at the rated power or a larger power close to the rated power. The temperature starts to rise from a low temperature until it stabilizes in a certain range. The concentration of pyrolytic particles and the content of harmful gases also tend to a stable state. In this case, it is not considered that a fire has occurred at the monitored object.

[0069] H3 shows a trend of gradually increasing, maintaining, and finally decreasing. This may be because the load increases in a certain period of time, and the power consumption decreases after a period of time, which causes the parameters to gradually increase, maintain, and finally decrease. This situation is also a normal phenomenon and does not indicate a fire at the monitored object.

[0070] H4 is a periodic change trend, which may be that the load has a periodic rise and fall process. This situation is also a normal phenomenon and it is not considered that a fire has occurred at the monitored object.

[0071] H5 is a relatively constant trend. The numerical value of the parameter changes very little and remains near a constant value, indicating that the monitored object may be in a normal working state without abnormalities, or it may be in a stable period of fire. Therefore, it is necessary to further judge in combination with the risk factor.

[0072] H6 shows a trend of first increasing in a short period of time and then returning to the initial state. This may be because the load increases in a short period of time and then returns to the initial state. This situation is also a normal phenomenon and it is not considered that a fire has occurred at the monitored object.

[0073] H7, H8 and H9 all show a load reduction trend, and the temperature, pyrolysis particle concentration and harmful gas content are gradually decreasing. At this time, the probability of fire is extremely low, so it is not considered that a fire has occurred at the monitored object.

[0074] In some embodiments, the step of calculating the risk factor in step S200 specifically includes: the risk factor K is calculated as follows:

[0075]

[0076] Wherein, i is any sampling moment or multiple consecutive sampling moments within a calculation cycle; when i is any sampling moment within a calculation cycle, PMx(i) is the PM value at the i sampling moment, and T(i) is the temperature value at the i sampling moment; when i is multiple consecutive sampling moments within a calculation cycle, PMx(i) and T(i) are both the average values ​​of the multiple consecutive sampling moments.

[0077] K is the correlation coefficient between gas particle content and temperature. Since the temperature increase is positively correlated with the gas particle content, it is defined as the risk factor K. The PM value can be one of the PM1.0, PM2.5, and PM10 particle contents or the sum of all particle contents. T is the temperature value. When the temperature rises to a certain value (for example, the temperature of the cable exceeds 80°C), the monitored object will decompose particles of various specifications and some large molecular harmful gases. Generally, the standard threshold of the risk factor can be 1.2.

[0078] In some embodiments, after step S300, the following steps are also included: after determining that a fire has occurred at the monitored object, determining the danger level of the fire, and issuing a corresponding fire alarm according to the danger level of the fire.

[0079] After confirming a fire, this embodiment can issue a corresponding fire alarm, so that relevant personnel can know the fire situation in time and take countermeasures in time to nip the fire risk in the bud.

[0080] At the same time, fires are divided into different danger levels, and different fire alarms are given for different danger levels. For example, when the danger level is high, a control signal can be sent to the sound and light alarm to make the sound and light alarm sound and light alarm, and it can also alarm the fire rescue departments such as the fire department and the hospital through the reserved port, and generate and record high-risk alarm events. When the danger level is low, a control signal can be sent to the sound and light alarm to make the sound and light alarm sound and light alarm, and generate and record low-risk alarm events. In this way, targeted rescue measures can be taken in time for different fire situations to avoid insufficient rescue forces and unnecessary waste of manpower and material resources.

[0081] Among them, the hazard level can be determined according to the hazard coefficient. Specifically, a mapping relationship between the hazard level and the hazard coefficient can be established. Each hazard level has a corresponding hazard coefficient range. The hazard coefficient range in which the hazard coefficient is located is determined, and then the hazard level is determined.

[0082] The embodiment of the present invention also provides an electrical fire monitoring and prediction device, such as Figure 4 As shown, including:

[0083] The parameter acquisition module 100 is used to obtain the temperature parameters, pyrolysis particle concentration parameters and air quality parameters of the monitored object in multiple calculation cycles;

[0084] The comprehensive calculation module 200 is used to calculate the change trend and risk factor of each parameter according to each parameter in multiple calculation cycles;

[0085] The fire prediction module 300 is used to predict whether a fire occurs at the monitored object based on the calculated change trends and risk factors of various parameters.

[0086] In some embodiments, when the change trend of any parameter is gradually increasing and the ratio of the risk factor to the standard threshold is greater than the set value, the fire prediction module 300 determines that a fire has occurred at the monitored object; or, when the change trend of any parameter is relatively constant and the risk factor is greater than the standard threshold, the fire prediction module 300 determines that a fire has occurred at the monitored object.

[0087] In some embodiments, the comprehensive calculation module 200 calculates the variation trend of each parameter according to the following method: first calculate the overall trend f(t) of each parameter,

[0088]

[0089] In which, each parameter has 2n sampling data points in a calculation cycle, n≥2; t is the time at the end of a calculation cycle; Sa(i) is the real-time value of each parameter at the sampling time;

[0090] Then calculate the subsequent trend g(t) of each parameter based on the 1 / 4 segment data at the end of the calculation cycle.

[0091]

[0092] make g(t)=G={def}, then multiply the matrix F and G to get the changing trend of each parameter Among them, the 9 results of F*G represent 9 changing trends of parameters, H1 is a gradual increase trend, H2 is a gradual increase and then stable trend, H3 is a gradual increase, then maintain, and finally a gradual decrease trend, H4 is a periodic change trend, H5 is a relatively constant trend, H6 is a short-term increase and then return to the initial state trend, H7, H8 and H9 are all load reduction trends.

[0093] In some embodiments, the comprehensive calculation module 200 calculates the risk factor according to the following method: The risk factor K is calculated as follows:

[0094]

[0095] Wherein, i is any sampling moment or multiple consecutive sampling moments within a calculation cycle; when i is any sampling moment within a calculation cycle, PMx(i) is the PM value at the i sampling moment, and T(i) is the temperature value at the i sampling moment; when i is multiple consecutive sampling moments within a calculation cycle, PMx(i) and T(i) are both the average values ​​of the multiple consecutive sampling moments.

[0096] In some embodiments, Figure 5 As shown, the electrical fire monitoring and prediction device of this embodiment further includes a fire alarm module 400, which is used to determine the danger level of the fire after determining that a fire has occurred at the monitored object, and to issue a corresponding fire alarm according to the danger level of the fire.

[0097] The above-mentioned embodiments of the electrical fire monitoring and prediction device are embodiments of the device class corresponding to the electrical fire monitoring and prediction method. For the specific description of the electrical fire monitoring and prediction device, reference can be made to the above-mentioned embodiments of the electrical fire monitoring and prediction method, which will not be repeated here.

[0098] The terms and words used in the above description and claims are not limited to the literal meanings, but are only used by the applicant to enable a clear and consistent understanding of the present invention. Therefore, it should be clear to those skilled in the art that the above description of various embodiments of the present invention is provided only for illustration, and not for limiting the present invention as defined by the attached claims and their equivalents.

Claims

1. A method for monitoring and predicting electrical fires, characterized in that: The steps include: Obtaining temperature parameters, pyrolysis particle concentration parameters and air quality parameters of the monitored object in multiple calculation cycles; According to various parameters in multiple calculation cycles, calculate the change trend and risk factor of each parameter; Based on the calculated change trends and risk factors of various parameters, it is predicted whether a fire will occur at the monitored object.

2. The electrical fire monitoring and prediction method according to claim 1, characterized in that: The step of predicting whether a fire has occurred at the monitored object based on the calculated change trends and risk factors of the various parameters specifically includes: when the change trend of any parameter is gradually increasing and the ratio of the risk factor to the standard threshold is greater than the set value, determining that a fire has occurred at the monitored object; or, when the change trend of any parameter is relatively constant and the risk factor is greater than the standard threshold, determining that a fire has occurred at the monitored object.

3. The electrical fire monitoring and prediction method according to claim 2, characterized in that: The step of calculating the changing trend of each parameter specifically includes: first calculating the overall trend f(t) of each parameter, In which, each parameter has 2n sampling data points in a calculation cycle, n≥2; t is the time at the end of a calculation cycle; Sa(i) is the real-time value of each parameter at the sampling time; Then calculate the subsequent trend g(t) of each parameter based on the 1 / 4 segment data at the end of the calculation cycle. make g(t)=G={def}, then multiply the matrix F and G to get the changing trend of each parameter Among them, the 9 results of F*G represent 9 changing trends of parameters, H1 is a gradual increase trend, H2 is a gradual increase and then stable trend, H3 is a gradual increase, then maintain, and finally a gradual decrease trend, H4 is a periodic change trend, H5 is a relatively constant trend, H6 is a short-term increase and then return to the initial state trend, H7, H8 and H9 are all load reduction trends.

4. The electrical fire monitoring and prediction method according to claim 2, characterized in that: The steps for calculating the risk factor specifically include: The risk factor K is calculated as follows: Wherein, i is any sampling moment or multiple consecutive sampling moments within a calculation cycle; when i is any sampling moment within a calculation cycle, PMx(i) is the PM value at the i sampling moment, and T(i) is the temperature value at the i sampling moment; when i is multiple consecutive sampling moments within a calculation cycle, PMx(i) and T(i) are both the average values ​​of the multiple consecutive sampling moments.

5. The electrical fire monitoring and prediction method according to any one of claims 1 to 4, characterized in that: The method further includes the following steps: after determining that a fire has occurred at the monitored object, determining the danger level of the fire, and issuing a corresponding fire alarm according to the danger level of the fire.

6. An electrical fire monitoring and prediction device, characterized in that: include: A parameter acquisition module is used to obtain temperature parameters, pyrolysis particle concentration parameters and air quality parameters of the monitored object in multiple calculation cycles; A comprehensive calculation module is used to calculate the change trend and risk factor of each parameter based on the parameters in multiple calculation cycles; The fire prediction module is used to predict whether a fire will occur at the monitored object based on the calculated change trends and risk factors of various parameters.

7. The electrical fire monitoring and prediction device according to claim 6, characterized in that: When the change trend of any parameter is gradually increasing and the ratio of the risk factor to the standard threshold is greater than the set value, the fire prediction module determines that a fire has occurred at the monitored object; or, when the change trend of any parameter is relatively constant and the risk factor is greater than the standard threshold, the fire prediction module determines that a fire has occurred at the monitored object.

8. The electrical fire monitoring and prediction device according to claim 7, characterized in that: The comprehensive calculation module calculates the changing trend of each parameter according to the following method: first calculate the overall trend f(t) of each parameter, In which, each parameter has 2n sampling data points in a calculation cycle, n≥2; t is the time at the end of a calculation cycle; Sa(i) is the real-time value of each parameter at the sampling time; Then calculate the subsequent trend g(t) of each parameter based on the 1 / 4 segment data at the end of the calculation cycle. make g(t)=G={def}, then multiply the matrix F and G to get the changing trend of each parameter Among them, the 9 results of F*G represent 9 changing trends of parameters, H1 is a gradual increase trend, H2 is a gradual increase and then stable trend, H3 is a gradual increase, then maintain, and finally a gradual decrease trend, H4 is a periodic change trend, H5 is a relatively constant trend, H6 is a short-term increase and then return to the initial state trend, H7, H8 and H9 are all load reduction trends.

9. The electrical fire monitoring and prediction device according to claim 7, characterized in that: The comprehensive calculation module calculates the risk factor according to the following method: The calculation method of the risk factor K is as follows: Wherein, i is any sampling moment or multiple consecutive sampling moments within a calculation cycle; when i is any sampling moment within a calculation cycle, PMx(i) is the PM value at the i sampling moment, and T(i) is the temperature value at the i sampling moment; when i is multiple consecutive sampling moments within a calculation cycle, PMx(i) and T(i) are both the average values ​​of the multiple consecutive sampling moments.

10. The electrical fire monitoring and prediction device according to any one of claims 6 to 9, characterized in that: It also includes a fire alarm module, which is used to determine the danger level of the fire after determining that a fire has occurred at the monitored object, and to issue a corresponding fire alarm according to the danger level of the fire.

Images