Intelligent identification and alarm method and system for unplanned power failure of coal mine

Abstract

The invention discloses a coal mine unplanned power failure intelligent identification and alarm method and system, and relates to the technical field of coal mine monitoring, and the method comprises the following steps: collecting the power data of a coal mine, and generating a circuit curve; and analyzing the circuit curve, determining abnormal information of the unplanned power failure, and giving an alarm prompt. According to the invention, omen information of unplanned power failure is accurately identified, an alarm is given in time, processing is carried out in time, the coal mine production process is prevented from being influenced, safety risks caused by sudden power failure are eliminated, comprehensive monitoring and intelligent analysis of a coal mine power system are realized, the safety and stability of the power system are improved, and the power system safety and reliability are improved. And a powerful guarantee is provided for safe production of a coal mine.

Description

Technical Field

[0001] The invention relates to the technical field of coal mine monitoring, and in particular to an intelligent identification and alarm method and system for unplanned power outages in coal mines. Background Art

[0002] Electricity resources are an important resource in the coal mine production process, but the existing technology lacks monitoring, which makes it impossible to accurately identify the precursor information of unplanned power outages and issue alarms in time, which will affect the coal mine production process. At the same time, sudden power outages will also pose corresponding safety risks. Summary of the invention

[0003] In view of the problems existing in the existing intelligent identification and alarm system for unplanned power outages in coal mines, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that it is impossible to accurately identify the precursor information of unplanned power outage and issue an alarm in time.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention provides a method for intelligently identifying and alarming unplanned power outages in coal mines, which comprises the following steps:

[0007] Collect power data from coal mines and generate circuit curves;

[0008] Analyze the circuit curve, determine the abnormal information of unplanned power outage, and issue an alarm.

[0009] As a preferred solution of the method for intelligent identification and alarm of unplanned power outages in coal mines described in the present invention, the power data includes voltage data, current data and power data.

[0010] As a preferred solution of the method for intelligent identification and alarm of unplanned power outages in coal mines described in the present invention, after collecting power data, the difference between adjacent data points in the detected circuit data is calculated, and a threshold K is set for comparison, and the corresponding sensor whose difference is greater than the threshold K is output, and the data points are sorted from small to large according to the number, and the sensor ranked first is used as the target current sensor.

[0011] As a preferred solution of the method for intelligent identification and alarm of unplanned power outage in coal mines of the present invention, the comparison method of the threshold value K and the difference value includes:

[0012] Acquire a first current signal of a target current sensor at a first moment;

[0013] respectively acquiring second current signals of other current sensors at the first moment;

[0014] Taking the first current signal as the center, establishing a first correlation relationship between a plurality of second current signals and the first current signal;

[0015] Acquire a third current signal of the target current sensor at a second moment;

[0016] respectively acquiring fourth current signals of other current sensors at the second moment;

[0017] Taking the third current signal as the center, establishing a second association relationship between a plurality of fourth current signals and the third current signal;

[0018] The first association relationship is compared with the second association relationship, and the current sensor with inconsistent comparison is determined as an abnormal current sensor and an alarm prompt is issued.

[0019] As a preferred solution of the method for intelligent identification and alarm of unplanned power outage in coal mines of the present invention, the collected power data of coal mines is preprocessed, specifically including:

[0020] Performing bit plane conversion on the current signal to determine characteristic information of the current signal at different bit levels;

[0021] Matching the characteristic information with the preset characteristic information, and when determining the match, using the current signal at the corresponding bit level as the target current signal;

[0022] Performing frame processing on the target current signal to obtain a plurality of frame sub-target current signals;

[0023] Calculating the noise intensity of the target current signal according to the sub-target current signals of a plurality of frames;

[0024] According to the noise intensity, a preset noise intensity-noise reduction coefficient table is searched to determine the noise reduction coefficient, and the target current signal is subjected to noise reduction processing according to the noise reduction coefficient to obtain preprocessed data;

[0025] Among them, the specific formula for calculating the noise intensity of the target current signal is:

[0026]

[0027] Wherein, Z is the noise intensity of the target current signal; P is the power parameter of the effective signal in the target current signal; λ is the matching error coefficient of the target current signal; N is the number of sub-target current signals; f i is the amplitude of the sub-target current signal of the i-th frame; is the average amplitude of the sub-target current signal of the frame.

[0028] As a preferred solution of the method for intelligent identification and alarm of unplanned power outage in coal mines of the present invention, the step of analyzing the circuit curve includes:

[0029] Performing feature recognition on the power curve based on the machine learning model to determine a first power feature;

[0030] Comparing the first power feature with the abnormal power feature, and when it is determined that the first power feature is consistent with the abnormal power feature, determining first abnormal information of the unplanned power outage and issuing an alarm prompt;

[0031] When it is determined that the first power feature is inconsistent with the abnormal power feature, acquiring a curve feature based on the power curve, generating a predicted power curve based on the curve feature, and calculating an effective coefficient of the predicted power curve;

[0032] When it is determined that the effective coefficient is greater than a preset effective coefficient threshold, feature recognition is performed on the predicted power curve based on the machine learning model to determine a second power feature;

[0033] The second power feature is compared with the abnormal power feature. When it is determined that the second power feature is consistent with the abnormal power feature, the second abnormal information of the unplanned power outage is determined and an alarm prompt is issued.

[0034] As a preferred solution of the method for intelligent identification and alarm of unplanned power outages in coal mines described in the present invention, after an alarm prompt occurs, the abnormal information and information associated therewith are uploaded to a database.

[0035] In a second aspect, an embodiment of the present invention provides an intelligent identification and alarm system for unplanned power outages in coal mines, which includes a data acquisition module, a data processing module, a data evaluation module, and an alarm module;

[0036] The data acquisition module is used to collect power data of the coal mine;

[0037] The data processing module is used to pre-process the collected power data;

[0038] The data evaluation module is used to analyze the circuit curve and output the analysis result;

[0039] The alarm module is used to generate an alarm prompt when abnormal information is determined.

[0040] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the processor executes the computer program, it implements any step of the above-mentioned method for intelligent identification and alarm of unplanned power outages in coal mines.

[0041] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the above-mentioned method for intelligent identification and alarm of unplanned power outages in coal mines is implemented.

[0042] The beneficial effects of the present invention are: accurately identifying the omen information of unplanned power outages, and issuing alarms and processing them in time to avoid affecting the production process of coal mines, while eliminating the safety risks caused by sudden power outages. It realizes comprehensive monitoring and intelligent analysis of coal mine power systems, which not only improves the safety and stability of the power system, but also provides a strong guarantee for the safe production of coal mines. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0044] Figure 1 This is a scenario diagram of the intelligent identification and alarm method for unplanned power outages in coal mines. DETAILED DESCRIPTION

[0045] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0046] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0047] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0048] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0049] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0050] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0051] Example 1

[0052] Reference Figure 1 , which is the first embodiment of the present invention, provides a method for intelligently identifying and alarming unplanned power outages in coal mines, comprising the following steps:

[0053] S1. Collect the power data of the coal mine and generate the circuit curve.

[0054] The power data includes voltage data, current data and power data.

[0055] After collecting power data, the difference between adjacent data points in the detected circuit data is calculated, and a threshold K is set for comparison. The corresponding sensors whose difference is greater than the threshold K are output, and the data points are sorted from small to large by the number, and the sensor ranked first is used as the target current sensor.

[0056] The comparison method between the threshold value K and the difference value includes:

[0057] Acquire a first current signal of a target current sensor at a first moment;

[0058] respectively acquiring second current signals of other current sensors at the first moment;

[0059] Taking the first current signal as the center, establishing a first correlation relationship between a plurality of second current signals and the first current signal;

[0060] Acquire a third current signal of the target current sensor at a second moment;

[0061] respectively acquiring fourth current signals of other current sensors at the second moment;

[0062] Taking the third current signal as the center, establishing a second association relationship between a plurality of fourth current signals and the third current signal;

[0063] The first association relationship is compared with the second association relationship, and the current sensor with inconsistent comparison is determined as an abnormal current sensor and an alarm prompt is issued.

[0064] The specific working principle is: calculate the current difference between adjacent data points in the detection data, compare these differences with the preset threshold value, and identify the data points with large current fluctuations. For each current sensor, count the number of adjacent data points whose corresponding difference is greater than the preset threshold value. Sort all current sensors from small to large according to this number. Select the current sensor with the first ranking as the target current sensor. The target current sensor is the current sensor with the smallest current fluctuation. Obtain the current signal of the target current sensor at the first moment (first current signal). Obtain the current signals of other current sensors at the same moment (second current signals) respectively. With the first current signal as the center, establish the association relationship (first association relationship) between other current signals and the first current signal. This association relationship is based on the relative difference, phase difference or other statistical measurement between the signals. Repeat the above process, but use the current signal at the second moment (third current signal and fourth current signal). With the third current signal as the center, establish the association relationship (second association relationship) between other current signals and the third current signal. Compare the first association relationship with the second association relationship to find inconsistencies. If a current sensor behaves inconsistently in the correlation between two moments (for example, the relative position with other sensors changes significantly), the sensor is marked as an abnormal current sensor, and an alarm is issued to notify relevant personnel to pay attention to and handle the abnormal current sensor.

[0065] At time t1, the first current signal A1 of the target current sensor and the second current signals of other current sensors, B1, C1 and D1, are obtained. With the first current signal as the center, the difference, sum or ratio information of other current sensors, B1, C1 and D1 and the first current signal A1 are determined respectively as the association relationship between each other current sensor and the target current sensor, thereby generating a first association relationship between several second current signals and the first current signal. At time t2, the first current signal A2 of the target current sensor and the second current signals of other current sensors, B2, C2 and D2, are obtained. Based on the same principle, a second association relationship between several fourth current signals and the third current signal is established. For the same other current sensor, the first association relationship is compared with the second association relationship. For example, B1 / A1 is compared with B2 / A2, and the current sensor with inconsistent comparison is determined as an abnormal current sensor and an alarm prompt is issued.

[0066] Facilitates accurate determination of abnormal current sensors, which can effectively identify and respond to abnormal conditions in the power system, and improve the reliability and safety of coal mine power monitoring. Through real-time monitoring and intelligent analysis, they can issue alarms in time to prevent potential power failures from adversely affecting coal mine production.

[0067] Preprocess the collected coal mine power data, including:

[0068] Performing bit plane conversion on the current signal to determine characteristic information of the current signal at different bit levels;

[0069] Matching the characteristic information with the preset characteristic information, and when determining the match, using the current signal at the corresponding bit level as the target current signal;

[0070] Performing frame processing on the target current signal to obtain a plurality of frame sub-target current signals;

[0071] Calculating the noise intensity of the target current signal according to the sub-target current signals of a plurality of frames;

[0072] According to the noise intensity, a preset noise intensity-noise reduction coefficient table is searched to determine the noise reduction coefficient, and the target current signal is subjected to noise reduction processing according to the noise reduction coefficient to obtain preprocessed data;

[0073] In this embodiment, the current signal in the preprocessed data is subjected to bit plane conversion. Bit plane conversion is a technology that separates the signal according to each bit of its binary representation, which can reveal the structure and characteristics of the signal at different bit levels. After conversion, characteristic information of the current signal at different bit levels (such as the highest bit, the second highest bit, etc.) can be obtained. The preset characteristic information is the characteristic information corresponding to the valid current signal. The target current signal is a determined valid signal, which facilitates the removal of invalid signals and reduces the amount of processed data;

[0074] The target current signal is processed by framing, that is, the continuous signal is divided into several shorter frames, which is helpful for processing non-stationary signals and reducing complexity in subsequent calculations. The noise intensity of the target current signal is calculated based on several frames of sub-target current signals. The preset noise intensity-noise reduction coefficient table is constructed based on experimental or empirical data and is used to map the noise intensity to the appropriate noise reduction coefficient. The target current signal is subjected to noise reduction processing using the determined noise reduction coefficient. Specific methods of noise reduction processing include filtering (such as low-pass filtering, band-pass filtering), wavelet transform denoising, spectral subtraction, etc. After noise reduction processing, the obtained pre-processed data is of higher quality, which significantly improves the quality of the current signal and lays a solid foundation for subsequent power curve generation and intelligent analysis.

[0075] Among them, the specific formula for calculating the noise intensity of the target current signal is:

[0076]

[0077] Wherein, Z is the noise intensity of the target current signal; P is the power parameter of the effective signal in the target current signal; λ is the matching error coefficient of the target current signal; N is the number of sub-target current signals; f i is the amplitude of the sub-target current signal of the i-th frame; is the average amplitude of the sub-target current signal of the frame.

[0078] S2. Analyze the circuit curve, determine the abnormal information of unplanned power outage, and issue an alarm.

[0079] The steps to analyze the circuit curve include:

[0080] Performing feature recognition on the power curve based on the machine learning model to determine a first power feature;

[0081] Comparing the first power feature with the abnormal power feature, and when it is determined that the first power feature is consistent with the abnormal power feature, determining first abnormal information of the unplanned power outage and issuing an alarm prompt;

[0082] When it is determined that the first power feature is inconsistent with the abnormal power feature, acquiring a curve feature based on the power curve, generating a predicted power curve based on the curve feature, and calculating an effective coefficient of the predicted power curve;

[0083] When it is determined that the effective coefficient is greater than a preset effective coefficient threshold, feature recognition is performed on the predicted power curve based on the machine learning model to determine a second power feature;

[0084] The second power feature is compared with the abnormal power feature. When it is determined that the second power feature is consistent with the abnormal power feature, the second abnormal information of the unplanned power outage is determined and an alarm prompt is issued.

[0085] The power curve is input into a pre-trained machine learning model, which can identify key features in the power curve (i.e., the first power feature), which includes a sudden drop in current, frequency fluctuation, phase shift, etc., which are closely related to the normal operating state of the power system. The identified first power feature is compared with the preset abnormal power feature. The abnormal power feature is pre-defined based on historical data and expert knowledge, and represents the characteristic pattern of unplanned power outages or other power abnormal events; if the first power feature is consistent with the abnormal power feature, it means that the current power system is experiencing an unplanned power outage or other abnormal situation. Once the abnormal situation is determined, the fourth determination module will immediately issue an alarm. The fourth determination module will notify relevant personnel to pay attention to and handle the abnormal situation; when the fourth determination module fails to determine the abnormal situation, the fifth determination module will further analyze the power curve and identify potential abnormal information through prediction and comparison. The specific steps are as follows: if the first power feature is inconsistent with the abnormal power feature, the fifth determination module will generate a predicted power curve based on the features of the current power curve (i.e., curve features), which involves time series analysis, regression analysis, or more complex machine learning algorithms to predict the operating state of the power system in the future, calculate the effective coefficient of the predicted power curve, which evaluates the accuracy and reliability of the prediction results, and compare the effective coefficient of the predicted power curve with the preset effective coefficient threshold. If the effective coefficient is greater than the threshold, it means that the prediction result is relatively reliable and can be further analyzed. The predicted power curve is feature-identified again to determine the second power feature, and the second power feature is compared with the abnormal power feature to identify potential abnormal situations. If the second power feature is consistent with the abnormal power feature, it means that although the current power system has not yet shown obvious abnormalities, according to the prediction results, unplanned power outages or other abnormal situations may occur in the future. When it is determined that there is a potential abnormal situation, the fifth determination module will issue an alarm prompt so that relevant personnel can take measures in advance to prevent or mitigate the impact of abnormal events. Through the collaborative work of the fourth determination module and the fifth determination module;

[0086] Among them, the calculation of the effective coefficient of the predicted power curve includes:

[0087] Cutting off the end curve segment of the power curve and the beginning curve segment of the predicted power curve; wherein the end curve segment of the power curve is equal to the beginning curve segment of the predicted power curve;

[0088] Perform correlation analysis on the terminal curve segment and the head curve segment to determine the maximum effective coefficient of the terminal curve segment and the head curve segment;

[0089] According to the maximum effective coefficient of the end curve segment and the head curve segment, the effective coefficient of the predicted power curve is calculated:

[0090]

[0091] Among them, β1 is the correction factor for the effective coefficient derived from the forward path; W1 is the effective coefficient of the predicted power curve derived from the forward path based on the maximum effective coefficient of the terminal curve segment and the head curve segment; β2 is the correction factor for the effective coefficient derived from the reverse path; W2 is the effective coefficient of the predicted power curve derived from the reverse path based on the maximum effective coefficient of the terminal curve segment and the head curve segment; λ is the attenuation parameter of the effective coefficient from the first predicted curve segment to the last predicted curve segment in the predicted power curve; W0 is the maximum effective coefficient of the terminal curve segment and the head curve segment; q is the probability that the intercepted terminal curve segment is a valid segment.

[0092] The end curve segment of the power curve: a segment of a certain length is cut from the end of the current power curve. This segment represents the recent state change of the power system. The head curve segment of the predicted power curve: a segment of the same length as the end curve segment is cut from the beginning of the predicted power curve. This segment represents the initial state of the predicted future power system. Use statistical methods or machine learning algorithms to perform correlation analysis on the end curve segment and the head curve segment to determine the similarity or correlation between them. This analysis can be based on a variety of indicators, such as correlation coefficient, mutual information, dynamic time warping (DTW) distance, etc. In the correlation analysis, find the coefficient that represents the maximum similarity or correlation between the two segments. This coefficient will serve as an important basis for evaluating the effectiveness of the predicted power curve. According to the maximum effective coefficient of the end curve segment and the head curve segment, the effective coefficient of the predicted power curve is calculated, and is a correction factor for the effective coefficient derived from the forward path and the reverse path, which is used to adjust the weight of the effective coefficient under different paths. It reflects the direct correlation from the current state to the predicted state. It reflects the natural attenuation of prediction accuracy as the prediction time increases. It is used to consider the impact of noise or outliers that may exist in the actual data on the analysis results. Accurately calculating the effective coefficient of the predicted power curve facilitates improving the accuracy of judging the effective coefficient of the predicted power curve and the value of the preset effective coefficient threshold, thereby accurately judging whether the predicted power curve is reliable.

[0093] After an alarm occurs, the abnormal information and related information are uploaded to the database.

[0094] Example 2

[0095] On the basis of the first embodiment, this embodiment further provides an intelligent identification and alarm system for unplanned power outages in coal mines, including a data acquisition module, a data processing module, a data evaluation module, and an alarm module;

[0096] The data acquisition module is used to collect power data of the coal mine;

[0097] The data processing module is used to pre-process the collected power data;

[0098] The data evaluation module is used to analyze the circuit curve and output the analysis result;

[0099] The alarm module is used to generate an alarm prompt when abnormal information is determined.

[0100] This embodiment also provides a computer device, which is suitable for the case of the intelligent identification and alarm method of unplanned power outages in coal mines, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the intelligent identification and alarm method of unplanned power outages in coal mines as proposed in the above embodiment.

[0101] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0102] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for intelligently identifying and alarming unplanned power outages in coal mines as proposed in the above embodiment is implemented.

[0103] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be found in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0104] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for intelligent identification and alarm of unplanned power outages in coal mines, characterized by: The following steps are included: Collect power data from coal mines and generate circuit curves; Analyze the circuit curve, determine the abnormal information of unplanned power outage, and issue an alarm.

2. The method for intelligent identification and alarming of unplanned power outages in coal mines according to claim 1, characterized in that: The electric power data includes voltage data, current data and power data.

3. The method for intelligent identification and alarming of unplanned power outages in coal mines according to claim 2, characterized in that: After collecting power data, the difference between adjacent data points in the detected circuit data is calculated, and a threshold K is set for comparison. The corresponding sensors whose difference is greater than the threshold K are output, and the data points are sorted from small to large by the number, and the sensor ranked first is used as the target current sensor.

4. The method for intelligent identification and alarming of unplanned power outages in coal mines according to claim 3, characterized in that: The comparison method between the threshold value K and the difference value includes: Acquire a first current signal of a target current sensor at a first moment; respectively acquiring second current signals of other current sensors at the first moment; Taking the first current signal as the center, establishing a first correlation relationship between a plurality of second current signals and the first current signal; Acquire a third current signal of the target current sensor at a second moment; respectively acquiring fourth current signals of other current sensors at the second moment; Taking the third current signal as the center, establishing a second association relationship between a plurality of fourth current signals and the third current signal; The first association relationship is compared with the second association relationship, and the current sensor with inconsistent comparison is determined as an abnormal current sensor and an alarm prompt is issued.

5. The method for intelligent identification and alarming of unplanned power outages in coal mines according to claim 4, characterized in that: Preprocess the collected coal mine power data, including: Performing bit plane conversion on the current signal to determine characteristic information of the current signal at different bit levels; Matching the characteristic information with the preset characteristic information, and when determining the match, using the current signal at the corresponding bit level as the target current signal; Performing frame processing on the target current signal to obtain a plurality of frame sub-target current signals; Calculating the noise intensity of the target current signal according to the sub-target current signals of a plurality of frames; According to the noise intensity, a preset noise intensity-noise reduction coefficient table is searched to determine the noise reduction coefficient, and the target current signal is subjected to noise reduction processing according to the noise reduction coefficient to obtain preprocessed data; Among them, the specific formula for calculating the noise intensity of the target current signal is: Wherein, Z is the noise intensity of the target current signal; P is the power parameter of the effective signal in the target current signal; λ is the matching error coefficient of the target current signal; N is the number of sub-target current signals; f i is the amplitude of the sub-target current signal of the i-th frame; f is the average amplitude of the sub-target current signal of the frame.

6. The method for intelligent identification and alarming of unplanned power outages in coal mines according to claim 5, characterized in that: The steps to analyze the circuit curve include: Performing feature recognition on the power curve based on the machine learning model to determine a first power feature; Comparing the first power feature with the abnormal power feature, and when it is determined that the first power feature is consistent with the abnormal power feature, determining first abnormal information of the unplanned power outage and issuing an alarm prompt; When it is determined that the first power feature is inconsistent with the abnormal power feature, acquiring a curve feature based on the power curve, generating a predicted power curve based on the curve feature, and calculating an effective coefficient of the predicted power curve; When it is determined that the effective coefficient is greater than a preset effective coefficient threshold, feature recognition is performed on the predicted power curve based on the machine learning model to determine a second power feature; The second power feature is compared with the abnormal power feature. When it is determined that the second power feature is consistent with the abnormal power feature, the second abnormal information of the unplanned power outage is determined and an alarm prompt is issued.

7. The method for intelligent identification and alarming of unplanned power outages in coal mines according to claim 6, characterized in that: After an alarm occurs, the abnormal information and related information are uploaded to the database.

8. An intelligent recognition and alarm system for unplanned power outages in coal mines, based on the intelligent recognition and alarm method for unplanned power outages in coal mines according to any one of claims 1 to 7, characterized in that: It includes data acquisition module, data processing module, data evaluation module, and alarm module; The data acquisition module is used to collect power data of the coal mine; The data processing module is used to pre-process the collected power data; The data evaluation module is used to analyze the circuit curve and output the analysis result; The alarm module is used to generate an alarm prompt when abnormal information is determined.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for intelligently identifying and alarming unplanned power outages in coal mines according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligently identifying and alarming unplanned power outages in coal mines according to any one of claims 1 to 7 are implemented.

Images