Temperature measurement method and system for underground mining electrical equipment based on infrared technology

Abstract

The present invention relates to the field of temperature measurement technology, and specifically to a method and system for measuring the temperature of underground mining electrical equipment based on infrared technology. The equipment temperature time series data and multiple environmental factor time series data of the monitoring points of underground mining electrical equipment are obtained, and based on the Markov chain concept, the environmental factor time series data are analyzed to determine the environmental state set of each monitoring point, and a transition probability matrix is ​​constructed to describe the evolution of the environmental state. At the same time, the equipment temperature state matrix is ​​constructed in combination with the equipment temperature value to reflect the equipment temperature under different environmental state transitions. According to the current environmental state set, the corresponding row matrix is ​​extracted, and the influence of the environmental state on the equipment temperature and the spatial distribution characteristics of the equipment temperature are considered, and the initial prediction matrix is ​​adjusted again to obtain the final prediction state matrix. Finally, the transition probability matrix, the final prediction state matrix and the next moment environmental state set are combined to achieve accurate measurement of the temperature of underground electrical equipment.

Description

Technical Field

[0001] The invention relates to the technical field of temperature measurement, and in particular to a temperature measurement method and system for underground mining electrical equipment based on infrared technology. Background Art

[0002] Underground mining electrical equipment is divided into general mining type and mining explosion-proof type according to whether there is gas or coal dust in the use environment. When the temperature of the equipment is too high, it is not only easy to reduce the durability of the equipment, but also because the environment in the mine is relatively closed, it may cause adverse effects such as explosions, and even cause mining accidents. Therefore, measuring the temperature of the equipment is of utmost importance. Infrared technology can obtain the temperature of the equipment without contact, and has the advantages of fast response and strong adaptability. Therefore, it is often used to measure the temperature of underground mining electrical equipment.

[0003] When using infrared technology to measure the temperature of underground mining electrical equipment, the existing technology usually directly uses the measured value as the actual temperature value. However, due to the complex underground environment, the ambient temperature, ambient humidity, dust concentration, etc. will affect the absorption rate of radiation on the equipment surface, so that the measured value cannot reflect the actual equipment temperature value. Therefore, if the equipment temperature value measured by infrared technology is directly used as the temperature value of underground mining electrical equipment, the temperature measurement accuracy will be low. Summary of the invention

[0004] In order to solve the problem that the underground environment is complex, the ambient temperature, ambient humidity, dust concentration, etc. will affect the absorption rate of radiation on the equipment surface, so that the measured value cannot reflect the real equipment temperature value. Therefore, if the equipment temperature value measured by infrared technology is directly used as the temperature value of underground mining electrical equipment, it will lead to the technical problem of low temperature measurement accuracy. The purpose of the present invention is to provide a temperature measurement method and system for underground mining electrical equipment based on infrared technology. The technical scheme adopted is as follows:

[0005] Obtain the equipment temperature time series data of each monitoring point on underground mining electrical equipment and the time series data of various environmental factors during the historical period;

[0006] Based on the values ​​of the environmental values ​​in the time series data of multiple environmental factors, the environmental state set of each monitoring point at each moment is determined; based on the transition between the environmental state sets of each monitoring point at adjacent moments in the time series, a transition probability matrix at each monitoring point is constructed, and combined with the device temperature values ​​in the device temperature time series data, a device temperature state matrix is ​​constructed;

[0007] According to the environmental state set of each monitoring point at the current moment, the corresponding row matrix is ​​extracted from the device temperature state matrix as the target matrix; the change correlation between the device temperature value and the environmental value of the environmental factor is analyzed to obtain the influencing factor of each environmental factor in each environmental state set so as to make an initial adjustment to the target matrix and obtain the initial prediction state matrix of each monitoring point at the current moment;

[0008] Based on the differences between the device temperature values ​​at the monitoring points, the initial prediction state matrix of each monitoring point at the current moment is adjusted again to obtain the final prediction state matrix of each monitoring point at the current moment;

[0009] Based on the transition probability matrix at each monitoring point, the final predicted state matrix of each monitoring point at the current moment and the environmental state set at the next moment, the temperature of underground mining electrical equipment is measured.

[0010] Furthermore, the environmental state set of each monitoring point at each moment is determined based on the environmental values ​​in the time series data of multiple environmental factors, including:

[0011] In each environmental factor time series data, the maximum environmental value and the minimum environmental value are each used as a boundary value to obtain a value range corresponding to each environmental factor, and the value range corresponding to each environmental factor is equally divided into a preset first number of value intervals;

[0012] All the numerical intervals of all environmental factors are combined to obtain all kinds of environmental state sets, and each environmental state set contains a numerical interval of each environmental factor;

[0013] At any moment, the environmental state set of each monitoring point at that moment is determined from all types of environmental state sets according to the numerical interval to which the environmental values ​​in all environmental factor time series data of each monitoring point at that moment belong.

[0014] Furthermore, the method for obtaining the transition probability matrix includes:

[0015] The behavior is the starting state and the column is the target state, so as to construct an initial probability matrix based on the set of all environmental states, and the element value of each position in the initial probability matrix is ​​0;

[0016] The environmental state set at each moment is taken as the initial state, and the environmental state set at the next moment adjacent to each moment is taken as the target state, so that the environmental state sets of two adjacent moments are taken as a state transition group, and the number of each state transition group is counted;

[0017] In the initial probability matrix, each element value is replaced by the number of state transition groups corresponding to the position of each element value, thereby obtaining an updated probability matrix;

[0018] All element values ​​in the update probability matrix are normalized, so as to obtain a transition probability matrix at each monitoring point.

[0019] Furthermore, the method for acquiring the device temperature state matrix includes:

[0020] The rows are the starting states and the columns are the target states, so as to construct the initial state matrix according to the set of all environmental states, and the element value of each position in the initial state matrix is ​​0;

[0021] In the transition probability matrix at each monitoring point, the element value corresponding to each position in the initial state matrix is ​​replaced by the mean of the device temperature values ​​at the corresponding time of the target state in all state transition groups corresponding to each position, thereby obtaining the device temperature state matrix at each monitoring point.

[0022] Furthermore, the method for obtaining the impact factor includes:

[0023] Choose one environmental factor as the target factor and the other environmental factors as reference factors;

[0024] All the value intervals of all the reference factors are combined to obtain all the reference combinations. Among all the types of environmental state sets corresponding to each reference combination, the environmental state set with the largest number of corresponding moments is taken as the target set;

[0025] A coordinate system is constructed based on the target factors and the device temperature, and all moments in the target set are mapped to the coordinate system and linearly fitted to obtain a fitting straight line;

[0026] The product of the difference between the median of the numerical interval of the target factor in each environmental state set and the preset target value corresponding to the target factor and the slope of the fitting straight line is taken as the influencing factor corresponding to the target factor.

[0027] Furthermore, the method for obtaining the initial prediction state matrix includes:

[0028] For any set of environmental states, the sum of the preset device temperature value and the influencing factors of all environmental factors under the set of environmental states is taken as the theoretical device temperature value corresponding to the set of environmental states;

[0029] Based on the element values ​​in the target matrix and the theoretical device temperature value, adjusting the element values ​​in the target matrix to obtain an updated value;

[0030] The element values ​​at the corresponding positions of the target matrix are replaced with the updated values ​​to obtain the initial predicted state matrix of each monitoring point at the current moment.

[0031] Furthermore, the method for obtaining the update value includes:

[0032] Counting the number of moments corresponding to each set of environmental states, taking an environmental state set with a number of moments greater than a preset second number as a normal state set, and taking an environmental state set with a number of moments less than or equal to the preset second number as a special state set;

[0033]

[0034] in, Represents the updated value at the i-th position in the target matrix; Represents the element value at the i-th position in the target matrix; The theoretical value of the device temperature of the environmental state set corresponding to the column at the i-th position in the target matrix; Indicates the preset weight.

[0035] Furthermore, the method for obtaining the final prediction state matrix includes:

[0036] For any monitoring point, calculate the mean of the device temperature values ​​at all times in each environmental state set of the monitoring point as the average state value of the monitoring point in each environmental state set;

[0037] Determine the preset neighborhood of each monitoring point on underground mining electrical equipment;

[0038] In the preset neighborhood of each monitoring point, for any set of environmental states, the difference between the average state value of each monitoring point under the set of environmental states and the average state value of all neighboring monitoring points is averaged to obtain the state structure performance value of each monitoring point under the set of environmental states;

[0039] Determine an adjustment factor based on the state structure performance value of each monitoring point under the environmental state set corresponding to the column where each element value in the initial prediction state matrix is ​​located, and the state structure performance value is negatively correlated with the adjustment factor;

[0040] Each element value in the initial prediction state matrix is ​​replaced by the product of each element value and the corresponding adjustment factor, so as to obtain the final prediction state matrix of each monitoring point at the current moment.

[0041] Furthermore, the temperature of underground mining electrical equipment is measured based on the transition probability matrix at each monitoring point, the final predicted state matrix of each monitoring point at the current moment, and the environmental state set at the next moment, including:

[0042] According to the set of environmental states at each monitoring point at the current moment, a corresponding row matrix is ​​extracted from the transition probability matrix as a comparison matrix;

[0043] If the element value of the position where the maximum element value in the final prediction state matrix at the current moment is located in the comparison matrix is ​​greater than the preset probability threshold, an early warning is required;

[0044] The element value of the environmental state set of each monitoring point at the next moment after the current moment in the corresponding column of the final prediction state matrix is ​​used as the equipment temperature value of each monitoring point on the underground mining electrical equipment at the next moment after the current moment.

[0045] A temperature measurement system for underground mining electrical equipment based on infrared technology comprises a processor and a memory. The memory stores at least one instruction, at least one program, a code set or an instruction set. When the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor, the steps of a temperature measurement method for underground mining electrical equipment based on infrared technology are implemented.

[0046] The present invention has the following beneficial effects:

[0047] By obtaining the equipment temperature time series data and multiple environmental factor time series data of each monitoring point on the underground mining electrical equipment in the historical period, the influence of the complex underground environment on the equipment temperature can be considered more comprehensively, and the accuracy of subsequent equipment temperature measurement can be improved. Since the change of the environment is a random process, the present invention is based on the idea of ​​Markov chain, analyzes the value of the environmental value in the time series data of multiple environmental factors, determines the environmental state set of each monitoring point at each moment, and the environmental state set characterizes the underground environment at each moment, and then constructs the transition probability matrix at each monitoring point based on the transition of the environmental state set of two adjacent moments in the time series, which is used to describe the state evolution of the underground environment at different time points, which helps to predict the influence of the change of the underground environment on the equipment temperature in the future, and, at the same time, in combination with the equipment temperature value, constructs the equipment temperature state matrix, and the element value in the matrix reflects the temperature of the equipment monitoring point under different underground environmental state transitions. Further, according to the environmental state set at the current moment, the corresponding row matrix is ​​extracted from the equipment temperature state matrix as the target matrix, and the influence factor of each environmental factor on each underground environmental state is analyzed, so as to adjust the target matrix for the first time and obtain the initial prediction state matrix. This process takes into account the impact of environmental conditions on equipment temperature, effectively improving the accuracy of subsequent predictions. In view of the fact that in actual use of electrical equipment, due to reasons such as rusted bolts and mechanical friction, the temperature measurement of monitoring points at different locations will fluctuate, so the present invention adjusts the initial prediction state matrix again based on the difference between the equipment temperature values ​​of the monitoring points to obtain the final prediction state matrix. This step takes into account the spatial distribution characteristics of the equipment temperature, further improving the accuracy of temperature measurement. Finally, based on the transition probability matrix, the final prediction state matrix and the set of environmental conditions at the next moment, the present invention can accurately measure the temperature of underground mining electrical equipment. This measurement method takes into account the impact of the complex environmental conditions underground on the equipment temperature measurement, and also analyzes the distribution of the surface temperature of the electrical equipment, which is conducive to improving the accuracy of the temperature measurement of underground mining electrical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0049] Figure 1 A method flow chart of a method for measuring temperature of underground mining electrical equipment based on infrared technology provided by one embodiment of the present invention;

[0050] Figure 2 A system block diagram of a temperature measurement system for underground mining electrical equipment based on infrared technology provided by an embodiment of the present invention;

[0051] Figure 3 A schematic diagram of the system structure of a temperature measurement system for underground mining electrical equipment based on infrared technology provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the temperature measurement method and system of underground mining electrical equipment based on infrared technology proposed by the present invention, its specific implementation method, structure, characteristics and effects as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0053] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0054] The following is a detailed description of a method and system for measuring temperature of underground mining electrical equipment based on infrared technology provided by the present invention in conjunction with the accompanying drawings.

[0055] See also Figure 1 , which shows a method flow chart of a method for measuring temperature of underground mining electrical equipment based on infrared technology provided by an embodiment of the present invention, the method comprising the following steps:

[0056] Step S1: Obtain the equipment temperature time series data and various environmental factor time series data of each monitoring point on underground mining electrical equipment during a historical period.

[0057] In underground mining environments such as coal mines, the safe operation of electrical equipment is one of the key factors to ensure production efficiency and personnel safety. Due to the complex and changeable underground environment, including various environmental factors such as ambient temperature, ambient humidity, dust concentration, ventilation conditions, etc., these complex and changeable environmental factors have a significant impact on the heat dissipation performance and temperature distribution of electrical equipment. If electrical equipment operates under high temperature or abnormal temperature conditions for a long time, it is very easy to cause failures or even fires, which seriously threatens mine safety, so it is necessary to accurately measure the temperature of underground mining electrical equipment.

[0058] With the development of infrared temperature measurement technology, non-contact temperature measurement has become a new trend in temperature monitoring of underground electrical equipment. Infrared temperature measurement technology has the advantages of wide measurement range, fast response speed, and no need for direct contact with the object being measured. It is very suitable for temperature monitoring of electrical equipment in complex underground environments. Therefore, a monitoring surface is set up outside the underground mining electrical equipment, so that the temperature of each monitoring point on the monitoring surface of the underground mining electrical equipment is measured using an infrared thermometer or an infrared thermal imager, so as to obtain the equipment temperature time series data in the historical period; in the same period, the sensor equipment is used to obtain the time series data of various environmental factors at each monitoring point.

[0059] It should be noted that in the embodiments of the present invention, environmental factors include but are not limited to ambient humidity, ambient temperature, dust concentration, etc., and the environmental factor time series data at each monitoring point can be obtained based on the corresponding sensors installed at each monitoring point, or sensors can be set at fixed positions underground to measure various environmental factor time series data, and the obtained environmental factor time series data can be used as the environmental factor time series data at each monitoring point; the historical period is set to 1 hour before the current moment, and the specific length of the period can be adjusted according to the implementation scenario, which is not limited here; the collection time interval of all data is set to 1s, and the specific time interval can also be adjusted according to the implementation scenario, which is not limited here.

[0060] Step S2: Based on the values ​​of the environmental values ​​in the time series data of multiple environmental factors, determine the environmental state set of each monitoring point at each moment; based on the transition between the environmental state sets of each monitoring point at adjacent moments in time series, construct a transition probability matrix at each monitoring point, and combine the device temperature values ​​in the device temperature time series data to construct a device temperature state matrix.

[0061] The Markov chain describes the state evolution of the system at different time points by defining a series of states and the transition probabilities between these states. The underground environment is complex and changeable. Therefore, the present invention uses the idea of ​​Markov chain to determine the environmental state set at each monitoring point by using the time series data of multiple environmental factors. The continuously changing time series data of environmental factors can be discretized into a finite number of environmental state sets, and the transition between environmental state sets can reflect the changing law of the underground environment. Thus, a transition probability matrix at each monitoring point is constructed to quantify this changing law; then, combined with the equipment temperature value, an equipment temperature state matrix is ​​constructed to describe the temperature conditions of electrical equipment under different environmental changes, which is of great significance for predicting the temperature of electrical equipment under future environmental conditions.

[0062] By dividing the continuously changing time series data of environmental factors into a finite set of environmental states, the subsequent analysis process can be simplified while retaining key information. Therefore, based on the environmental values ​​in the time series data of multiple environmental factors, the environmental state set of each monitoring point at each moment is determined.

[0063] Preferably, in one embodiment of the present invention, the method for determining the set of environmental states of each monitoring point at each moment includes:

[0064] In each environmental factor time series data, the maximum environmental value and the minimum environmental value are each used as a boundary value to obtain a value range corresponding to each environmental factor, and the value range corresponding to each environmental factor is equally divided into a preset first number of value intervals.

[0065] Then, all the numerical intervals of all the environmental factors are combined to obtain all kinds of environmental state sets, and each environmental state set contains a numerical interval of each environmental factor.

[0066] Finally, for any moment, the environmental state set of each monitoring point at that moment is determined from all types of environmental state sets according to the numerical interval to which the environmental values ​​in the time series data of all environmental factors of each monitoring point at that moment belong.

[0067] The above process is illustrated by an example: taking two environmental factors (ambient temperature and ambient humidity) as an example, assuming that within the preset historical period, the ambient temperature value range of monitoring point a is [10,30], and the ambient humidity value range is [20,50]. If the preset first number is set to 10, the numerical range corresponding to the ambient temperature is [10,12), [12,14), [14,16), ... [28,30]; the numerical range corresponding to the ambient humidity is [20,23), [23,26), [26,29), ... [47,50]; then it can be obtained There are 10 kinds of ambient temperature states × 10 kinds of ambient humidity states, a total of 100 kinds of ambient state sets, and each ambient state set contains a numerical interval corresponding to the ambient temperature and a numerical interval corresponding to the ambient humidity, such as {[10,12), [20,23)}; at this time, for any moment, if the ambient value of the monitoring point a in the ambient temperature environmental factor time series data at this moment is 15, and the ambient value of the ambient humidity environmental factor time series data is 28, then the ambient state set of the monitoring point a at this moment is {[14,16), [26,29)}.

[0068] It should be noted that the preset first number can be adjusted according to the implementation scenario and is not limited here. The underground environmental conditions at each moment belong to an environmental state set, that is, a state environment set may correspond to underground environmental conditions at multiple moments.

[0069] The transition probability matrix in the Markov chain defines the probability of the system transitioning from one state to another. Based on this matrix, we can understand the state evolution of the system at different time points, that is, how the previous state in time sequence affects the future state. Therefore, when applied to the embodiment of the present invention, the transition probability matrix at each monitoring point can be constructed based on the transition between the sets of environmental states at each monitoring point at adjacent moments in time sequence, thereby quantifying the transition between the sets of environmental states at adjacent moments in time sequence at each monitoring point, capturing the dynamic changes of environmental states over time, and helping to predict the impact of future changes in the underground environment on the temperature of the equipment.

[0070] Preferably, in one embodiment of the present invention, the method for obtaining the transition probability matrix includes:

[0071] Based on the above process, all environmental state sets of the underground environment in the historical period can be obtained, so the behavior starting state can be listed as the target state, so as to construct an initial probability matrix based on all environmental state sets, and the element value of each position in the initial probability matrix is ​​0, thereby clarifying the state space and clearly expressing the potential transfer relationship between all environmental state sets in the form of a matrix: each position in the initial probability matrix represents the situation of transitioning from one environmental state set to another environmental state set.

[0072] Since the Markov chain is applicable to a system in which the current state depends only on the previous state, in the embodiment of the present invention, the set of environmental states at each moment is taken as the initial state, and the set of environmental states at the next moment adjacent to each moment is taken as the target state, so that the sets of environmental states at two adjacent moments are taken as a state transition group; at this time, any two adjacent moments correspond to a state transition group, and the two sets of environmental states in the state transition group represent the transition of the underground environment from one state to another.

[0073] Then count the number of each state transition group. Taking time 1, time 2, time 3, and time 4 as examples, the state transition group between time 1 and time 2 is the transformation of environment state set 1 to environment state set 2, the state transition group between time 2 and time 3 is the transformation of environment state set 3 to environment state set 4, and the state transition group between time 3 and time 4 is the transformation of environment state set 1 to environment state set 2; then the number of state transition groups (environment state set 1, environment state set 2) is 2, and the number of state transition groups (environment state set 3, environment state set 4) is 1.

[0074] Then, in the initial probability matrix, each element value is replaced by the number of state transition groups corresponding to the position of each element value, so as to obtain the updated probability matrix. For example, the position at the first row and second column in the initial probability matrix represents the transition from environment state set 1 to environment state set 2, so the element value at the first row and first column is the number of state transition groups (environment state set 1, environment state set 2).

[0075] Finally, all element values ​​in the update probability matrix are normalized to obtain the transition probability matrix at each monitoring point.

[0076] It should be noted that in other embodiments of the present invention, since there is a state transition group corresponding to each two adjacent moments, if there are 10 moments, then there are 9 state transition groups. In this case, the element value of each position in the transition probability matrix can also be directly set to the ratio of the number of state transition groups corresponding to each position to (the total number of moments - 1).

[0077] The transition probability matrix can be used to describe the probability of occurrence of different state evolutions in the underground environment. At the same time, the equipment temperature value in the equipment temperature time series data can be combined to construct an equipment temperature state matrix, which can reflect the temperature conditions of the monitoring points on the electrical equipment under different state evolutions of the underground environment.

[0078] Preferably, in one embodiment of the present invention, the method for acquiring the device temperature state matrix includes:

[0079] Similarly, the rows are taken as the starting states and the columns are taken as the target states, so as to construct the initial state matrix according to the set of all environmental states, and the element value of each position in the initial state matrix is ​​0.

[0080] Then, in the transition probability matrix at each monitoring point, the element value corresponding to each position in the initial state matrix is ​​replaced by the mean of the equipment temperature values ​​at the corresponding moment of the target state in all state transition groups corresponding to each position, thereby obtaining the equipment temperature state matrix at each monitoring point. Each element value in the temperature state matrix represents the temperature condition of the electrical equipment when the underground environment changes from one state to another.

[0081] For example: For example, the position in the first row and second column of the initial state matrix represents the transition from environmental state set 1 to environmental state set 2. If there are 2 state transition groups (environmental state set 1, environmental state set 2), which are the downhole environmental state transitions between time 1 and time 2 and the downhole environmental state transitions between time 3 and time 4, then the target state (environmental state set 2) in the state transition group (environmental state set 1, environmental state set 2) corresponds to two time moments (time 2 and time 4), so the element value in the first row and second column of the initial state matrix is ​​the average of the equipment temperature values ​​at time 2 and time 4.

[0082] At this point, the transition probability matrix and the equipment temperature state matrix can be constructed through the equipment temperature time series data in the historical period and the time series data of various environmental factors. At the same time, the state space of the underground environment (composed of all environmental state sets) is also constructed.

[0083] Step S3: According to the environmental state set of each monitoring point at the current moment, the corresponding row matrix is ​​extracted from the equipment temperature state matrix as the target matrix; the change correlation between the equipment temperature value and the environmental value of the environmental factor is analyzed to obtain the influencing factor of each environmental factor in each environmental state set so as to make an initial adjustment to the target matrix and obtain the initial predicted state matrix of each monitoring point at the current moment.

[0084] Since the element value at each position in the equipment temperature state matrix can represent the temperature condition at the equipment monitoring point when the downhole environment changes from one state to another, and the rows in the equipment temperature state matrix represent the initial state of the downhole environment, and the columns represent the target state of the downhole environment, the corresponding row matrix can be extracted from the equipment temperature state matrix according to the environmental state set of each monitoring point at the current moment as the target matrix. The target matrix represents the transition from the environmental state set of the downhole at the current moment to other environmental state sets, and each element value in the target matrix represents the potential possible value of the equipment temperature value at the next moment. Then, in view of the complex underground environment, the ambient temperature, ambient humidity, dust concentration, etc. will affect the absorption rate of radiation on the equipment surface, and the state components are combined in the form of a set, and only analyzed from a statistical aspect. There is a lack of analysis of real environmental factors, and thus a lack of credibility. Therefore, in an embodiment of the present invention, the impact of environmental factors on the equipment temperature is analyzed, and the impact factor of each environmental factor in each environmental state set is obtained, so as to make an initial adjustment to the element values ​​in the target matrix, and obtain the initial predicted state matrix of each monitoring point at the current moment, thereby preliminarily improving the prediction accuracy of the temperature value of the electrical equipment at each monitoring point at the next moment.

[0085] First, the impact factor of each environmental factor in each set of environmental states needs to be calculated.

[0086] Preferably, in one embodiment of the present invention, the method for obtaining the impact factor includes:

[0087] Select any one environmental factor as the target factor and the other environmental factors as reference factors.

[0088] All the numerical intervals of all the reference factors are combined to obtain all the reference combinations. Among all the types of environmental state sets corresponding to each reference combination, the environmental state set with the largest number of corresponding moments is taken as the target set.

[0089] A coordinate system is constructed based on the target factors and the device temperature, and all moments in the target set are mapped to the coordinate system and linearly fitted to obtain a fitting line.

[0090] An example of obtaining a fitting straight line is given below: the environmental factors include ambient temperature, ambient humidity and dust concentration. The target element is ambient temperature, and the reference factors are ambient humidity and dust concentration. All numerical intervals of ambient humidity and dust concentration are combined to obtain all reference combinations. At this time, each reference combination contains two environmental factors, and each environmental state set contains three environmental factors. Therefore, there should be a one-to-many relationship between the environmental state set and the reference combination. For example, a reference combination of ambient humidity and dust concentration {[20,23), [47,50)} corresponds to an environmental state set that may include {[10,12), [20,23), [47,50)}, {[14,16), [20,23), [47,50)}, {[28,30), [20,23), [47,50)}, etc. Then, each environmental state set corresponds to multiple moments. In order to analyze the impact of ambient temperature on device temperature, in an embodiment of the present invention, the environmental state set with the largest number of corresponding moments is selected as the target set. For example, the environmental state set {[10,12), [20,23), [47,50)} is selected. At this time, through the above process, a target set can be selected from the environmental state set corresponding to each reference combination, and each target set represents an environmental state where the ambient temperature value appears most frequently under certain ambient humidity and dust concentration. Then, a coordinate system can be constructed with ambient temperature as the horizontal axis and device temperature as the vertical axis, so as to map all moments in the target set to the coordinate system, and perform linear fitting on the data points in the coordinate system based on the least squares method to obtain a fitting straight line.

[0091] The trend of the fitted straight line can reflect the changing correlation between the target factor and the device temperature, and then analyze the impact. When the slope of the fitted straight line is positive, it means that as the ambient temperature increases, the device temperature will also increase; conversely, if the slope of the fitted straight line is negative, it means that as the ambient temperature increases, the device temperature will decrease.

[0092] Finally, the difference between the median of the numerical interval of the target factor in each environmental state set and the preset target value corresponding to the target factor is calculated. The difference can characterize the deviation between the value of the target factor in each environmental state set and the preset target value. The larger the value, the greater the degree of deviation of the target factor from the preset target value, which means that the influence of the target factor on the device temperature in this environmental state set may increase. Therefore, the product of the difference and the slope of the fitting line is used as the influencing factor corresponding to the target factor. The influencing factor corresponding to a certain environmental state set is positive, and the larger it is, the greater the positive influence of the target factor in each environmental set on the device temperature. Conversely, when the influencing factor corresponding to a certain environmental state set is negative, and the smaller it is, the greater the negative influence of the target factor in each environmental set on the device temperature.

[0093] It should be noted that the process of obtaining a fitting straight line based on the least squares method is a well-known technology and will not be elaborated here; the preset target value corresponding to each environmental factor is set to the minimum value in the corresponding environmental state time series data (it is believed that the impact of the environment on infrared radiation is minimal at this time).

[0094] Based on the above process, the influencing factors of each environmental factor in each environmental state set can be obtained, and then the target matrix can be initially adjusted based on the obtained indicators to obtain the initial prediction state matrix of each monitoring point at the current moment.

[0095] Preferably, in one embodiment of the present invention, the method for obtaining the initial prediction state matrix includes:

[0096] For any set of environmental states, the sum of the preset device temperature value and the influencing factors of all environmental factors under the environmental state set is taken as the theoretical device temperature value corresponding to the environmental state set. The theoretical device temperature value under each environmental state set represents the temperature value that the electrical equipment should theoretically have under the joint action of multiple environmental factors in each environmental state set.

[0097] Combine the theoretical equipment temperature value of each monitoring point on the electrical equipment under each set of environmental conditions with the element value in the target matrix.

[0098] Based on the element values ​​in the target matrix and the theoretical device temperature values, the element values ​​in the target matrix are adjusted to obtain updated values: Since the device temperature values ​​in actual production applications may deviate from the theoretical device temperature values ​​to a certain extent under the influence of various factors, in an embodiment of the present invention, the number of moments corresponding to each environmental state set is counted, and the environmental state set with a moment number greater than a preset second number is taken as a normal state set. The normal state set represents an environmental state set that often appears in actual production applications. In this environmental state set, the actual device temperature value, that is, the element value in the target matrix should be increased in weight. Conversely, the environmental state set with a moment number less than or equal to the preset second number is taken as a special state set. In the special state set, since the amount of data in actual production applications is small, the weight of the theoretical device temperature value should be increased. Based on this logic, the following formula model is constructed to obtain the updated value corresponding to each position in the target matrix;

[0099]

[0100] in, Represents the updated value at the i-th position in the target matrix; Represents the element value at the i-th position in the target matrix; The theoretical device temperature value of the environmental state set corresponding to the column at the i-th position in the target matrix; Indicates the preset weight.

[0101] In the formula model of the updated value, since the rows in the target matrix represent the starting state and the columns represent the target state, the column where the i-th element is located is a normal state set, which means that the target state is a normal state set. Based on the above logical analysis, the value of the preset weight should be (0.5, 1). In the embodiment of the present invention, the preset weight is set to 0.7.

[0102] Finally, the element values ​​at the corresponding positions of the target matrix are replaced with the updated values ​​to obtain the initial predicted state matrix of each monitoring point at the current moment.

[0103] It should be noted that the preset device temperature value is set to the average of the device temperature values ​​at all times in the environmental state set with the smallest value interval; the preset second number is set to one-tenth of the total number of moments rounded up, and the specific value can be adjusted according to the implementation scenario and is not limited here.

[0104] Step S4: Based on the differences between the device temperature values ​​at the monitoring points, the initial prediction state matrix of each monitoring point at the current moment is adjusted again to obtain the final prediction state matrix of each monitoring point at the current moment.

[0105] In actual use, due to the possible rusting of bolts, mechanical friction, and noise interference of underground mining electrical equipment, temperature fluctuations may occur between monitoring points on the surface of the electrical equipment. Therefore, in an embodiment of the present invention, based on the difference in equipment temperature between the monitoring points, the initial predicted state matrix of each monitoring point at the current moment is adjusted again to obtain the final predicted state matrix of each monitoring point at the current moment.

[0106] Preferably, in one embodiment of the present invention, the method for obtaining the final prediction state matrix includes:

[0107] For any monitoring point, calculate the average value of the equipment temperature at all times in each environmental state set of the monitoring point as the average state value of the monitoring point in each environmental state set.

[0108] Then, the preset neighborhood of each monitoring point on the underground mining electrical equipment is determined, and within the preset neighborhood of each monitoring point, for any environmental state set, the difference between the average state value of each monitoring point under the environmental state set and the average state value of all neighboring monitoring points is averaged to obtain the state structure performance value of each monitoring point under the environmental state set. If the state structure performance value is positive and the larger it is, the greater the degree to which the equipment temperature value of each monitoring point under the environmental state set is higher than that of the neighboring monitoring points, then it should be reduced in the subsequent process. Conversely, if the state structure performance value is negative and the smaller it is, the greater the degree to which the equipment temperature value of each monitoring point under the environmental state set is lower than that of the neighboring monitoring points, then it should be increased in the subsequent process.

[0109] Based on the state structure performance value of each monitoring point under the environmental state set corresponding to the column where each element value in the initial prediction state matrix is ​​located, the adjustment factor is determined, and the state structure performance value is positively correlated with the adjustment factor. The formula model of the adjustment factor includes:

[0110]

[0111] in, Represents the adjustment factor corresponding to the i-th element value in the initial prediction state matrix; Represents the state structure performance value under the environmental state set corresponding to the column where the i-th element value in the initial prediction state matrix is ​​located; represents the hyperbolic tangent function.

[0112] In the formula model of the adjustment factor, since the state structure performance value may be positive or negative, the hyperbolic tangent function is used to adjust the value in the embodiment of the present invention so that the adjusted The value range is adjusted to (-1, 1). Based on the above logic, when the state structure value is positive and the larger it is, the greater the degree to which the device temperature value should be reduced; conversely, when the state structure value is negative and the smaller it is, the greater the degree to which the device temperature value should be increased, so the preset constant 1 is set to The difference is used as the adjustment factor to implement the above logic.

[0113] Finally, each element value in the initial prediction state matrix is ​​replaced by the product of each element value and the corresponding adjustment factor, so as to obtain the final prediction state matrix of each monitoring point at the current moment.

[0114] It should be noted that the preset neighborhood is set as a circular range with each monitoring point as the center and a radius of 3. The specific size can be adjusted according to the implementation scenario and is not limited here.

[0115] Step S5: Based on the transition probability matrix at each monitoring point, the final predicted state matrix of each monitoring point at the current moment, and the environmental state set at the next moment, the temperature of the underground mining electrical equipment is measured.

[0116] Based on the above steps, after analyzing the data in the historical period, we can obtain the transition probability matrix at each monitoring point on the electrical equipment and the final predicted state matrix of each monitoring point at the current moment. Each element value in the final predicted state matrix represents the possible equipment temperature value of the monitoring point when it changes from one state to another. Therefore, the temperature of underground mining electrical equipment can be measured in combination with the environmental state set of each monitoring point at the next moment.

[0117] Preferably, in one embodiment of the present invention, based on the transition probability matrix at each monitoring point, the final predicted state matrix of each monitoring point at the current moment, and the environmental state set at the next moment, the temperature of underground mining electrical equipment is measured, including:

[0118] The transition probability matrix can describe the changes in the underground environment within a preset historical period. Therefore, according to the set of environmental states at each monitoring point at the current moment, the corresponding row matrix is ​​extracted from the transition probability matrix as a comparison matrix. The element value at each position in the comparison matrix represents the probability of occurrence of the transition from the set of environmental states corresponding to the rows of the comparison matrix to the set of environmental states corresponding to the columns of the comparison matrix.

[0119] Therefore, if the element value of the position of the maximum element value in the final predicted state matrix at the current moment in the comparison matrix is ​​greater than the preset probability threshold, it means that there is a high probability that the equipment may have high temperature at the next moment, and an early warning is required to help the staff prepare for maintenance in advance.

[0120] Then, the environmental state of each monitoring point at the next moment after the current moment is collected in the element value of the corresponding column in the final predicted state matrix as the equipment temperature value of each monitoring point on the underground mining electrical equipment at the next moment after the current moment, thereby realizing the temperature measurement of the underground mining electrical equipment.

[0121] It should be noted that the preset probability threshold is set to 0.7, and the specific value can be adjusted according to the implementation scenario and is not limited here; if the environmental values ​​corresponding to various environmental factors at the next moment of the current moment do not exist in the state space constructed by the environmental factor time series data in the preset historical period, the actual measured value of the device temperature at the next moment of the current moment will be used as the device temperature value.

[0122] In summary, by obtaining the equipment temperature time series data of each monitoring point on the underground mining electrical equipment in the historical period and the environmental time series data of multiple factors, the influence of the complex underground environment on the equipment temperature can be considered more comprehensively, and the accuracy of subsequent equipment temperature measurement can be improved. Since the change of the environment is a random process, the present invention is based on the idea of ​​Markov chain, and is analyzed based on the value of the environmental value of the time series data of multiple environmental factors, and the environmental state set of each monitoring point at each moment is determined. The environmental state set characterizes the underground environmental situation at each moment, and then based on the transition of the environmental state set of two adjacent moments in the time series, a transition probability matrix at each monitoring point is constructed to describe the state evolution of the underground environment at different time points, which is helpful to predict the influence of future changes in the underground environment on the equipment temperature, and, at the same time, in combination with the equipment temperature value, an equipment temperature state matrix is ​​constructed, and the element values ​​in the matrix reflect the temperature of the equipment monitoring point under different underground environmental state transitions. Further, according to the current environmental state set, the corresponding row matrix is ​​extracted from the equipment temperature state matrix as the target matrix, and by analyzing the influence factor of each environmental factor on each underground environmental state, the target matrix is ​​adjusted for the first time to obtain the initial prediction state matrix. This process takes into account the influence of the environmental state on the equipment temperature, and effectively improves the real-time and accuracy of subsequent predictions. In view of the fact that in actual use of electrical equipment, due to reasons such as rust of bolts and mechanical friction, the temperature measurement of monitoring points at different positions will fluctuate, so the present invention adjusts the initial prediction state matrix again based on the difference between the equipment temperature values ​​of the monitoring points to obtain the final prediction state matrix. This step takes into account the spatial distribution characteristics of the equipment temperature and further improves the accuracy of temperature measurement. Finally, based on the transition probability matrix, the final prediction state matrix and the environmental state set at the next moment, the embodiment of the present invention can accurately measure the temperature of underground mining electrical equipment. This measurement method takes into account the influence of the complex environmental state of the underground on the equipment temperature measurement, and also analyzes the distribution of the surface temperature of the electrical equipment, which is conducive to improving the accuracy of the temperature measurement of underground mining electrical equipment.

[0123] The embodiment of the present invention also proposes a temperature measurement system for underground mining electrical equipment based on infrared technology, see Figure 2 , which shows a system block diagram, including a data acquisition module 201, used to implement step S1 in the above method embodiment; a matrix construction module 202, used to implement step S2 in the above method embodiment; a matrix correction module 203, used to implement steps S3 and S4 in the above method embodiment; a temperature measurement module 204, used to implement step S5 in the above method embodiment.

[0124] It should be noted that the system provided in the above embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, the temperature measurement system for underground mining electrical equipment based on infrared technology and the temperature measurement method for underground mining electrical equipment based on infrared technology provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0125] See also Figure 3 , which shows a system structure diagram of an underground mining electrical equipment temperature measurement system based on infrared technology provided by an embodiment of the present invention, including a processor 300, a memory 301, a bus 302 and a communication interface 303, wherein the processor 300, the communication interface 303 and the memory 301 are connected via the bus 302; wherein the memory 301 may include a high-speed random access memory, the bus 302 may be an ISA bus, a PCI bus or an EISA bus, etc., and the processor 300 may be an integrated circuit chip with signal processing capabilities; the memory 301 stores at least one instruction, at least one program, a code set or an instruction set, and when the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor, the steps in a method for measuring the temperature of underground mining electrical equipment based on infrared technology are implemented.

[0126] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0127] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for measuring the temperature of underground mining electrical equipment based on infrared technology, characterized in that: The method comprises: Obtain the equipment temperature time series data of each monitoring point on underground mining electrical equipment and the time series data of various environmental factors during the historical period; Based on the values ​​of environmental values ​​in the time series data of multiple environmental factors, the environmental state set of each monitoring point at each moment is determined; based on the transition between the environmental state sets of each monitoring point at adjacent moments in the time series, a transition probability matrix is ​​constructed at each monitoring point, and combined with the equipment temperature values ​​in the equipment temperature time series data, an equipment temperature state matrix is ​​constructed; the transition probability matrix is ​​used to characterize the probability of occurrence of the underground environment under different state evolutions, and the equipment temperature state matrix is ​​used to characterize the temperature conditions of the monitoring points on the electrical equipment under different state evolutions of the underground environment; According to the environmental state set of each monitoring point at the current moment, the corresponding row matrix is ​​extracted from the equipment temperature state matrix as the target matrix, and the target matrix is ​​used to characterize the transition from the environmental state set of the well at the current moment to other environmental state sets; the correlation between the change of the equipment temperature value and the environmental value of the environmental factor is analyzed to obtain the influencing factor of each environmental factor in each environmental state set, thereby making an initial adjustment to the target matrix to obtain the initial prediction state matrix of each monitoring point at the current moment; Based on the differences between the device temperature values ​​at the monitoring points, the initial prediction state matrix of each monitoring point at the current moment is adjusted again to obtain the final prediction state matrix of each monitoring point at the current moment; Based on the transition probability matrix at each monitoring point, the final predicted state matrix of each monitoring point at the current moment and the environmental state set at the next moment, the temperature of underground mining electrical equipment is measured; The environmental state set of each monitoring point at each moment is determined based on the environmental values ​​in the time series data of multiple environmental factors, including: In each environmental factor time series data, the maximum environmental value and the minimum environmental value are each used as a boundary value to obtain a value range corresponding to each environmental factor, and the value range corresponding to each environmental factor is equally divided into a preset first number of value intervals; All the numerical intervals of all environmental factors are combined to obtain all kinds of environmental state sets, and each environmental state set contains a numerical interval of each environmental factor; For any moment, according to the numerical interval to which the environmental values ​​in the time series data of all environmental factors of each monitoring point at that moment belong, the environmental state set of each monitoring point at that moment is determined from all types of environmental state sets; The method for obtaining the transition probability matrix includes: The behavior is the starting state and the column is the target state, so as to construct an initial probability matrix based on the set of all environmental states, and the element value of each position in the initial probability matrix is ​​0; The environmental state set at each moment is taken as the initial state, and the environmental state set at the next moment adjacent to each moment is taken as the target state, so that the environmental state sets of two adjacent moments are taken as a state transition group, and the number of each state transition group is counted; In the initial probability matrix, each element value is replaced by the number of state transition groups corresponding to the position of each element value, thereby obtaining an updated probability matrix; All element values ​​in the update probability matrix are normalized, so as to obtain a transition probability matrix at each monitoring point.

2. The method for measuring temperature of underground mining electrical equipment based on infrared technology according to claim 1 is characterized in that: The method for obtaining the device temperature state matrix includes: The rows are the starting states and the columns are the target states, so as to construct the initial state matrix according to the set of all environmental states, and the element value of each position in the initial state matrix is ​​0; In the transition probability matrix at each monitoring point, the element value corresponding to each position in the initial state matrix is ​​replaced by the mean of the device temperature values ​​at the corresponding time of the target state in all state transition groups corresponding to each position, thereby obtaining the device temperature state matrix at each monitoring point.

3. The method for measuring temperature of underground mining electrical equipment based on infrared technology according to claim 1 is characterized in that: The method for obtaining the impact factor includes: Choose one environmental factor as the target factor and the other environmental factors as reference factors; All the value intervals of all the reference factors are combined to obtain all the reference combinations. Among all the types of environmental state sets corresponding to each reference combination, the environmental state set with the largest number of corresponding moments is taken as the target set; A coordinate system is constructed based on the target factors and the device temperature, and all moments in the target set are mapped to the coordinate system and linearly fitted to obtain a fitting straight line; The product of the difference between the median of the numerical interval of the target factor in each environmental state set and the preset target value corresponding to the target factor and the slope of the fitting straight line is taken as the influencing factor corresponding to the target factor.

4. The method for measuring temperature of underground mining electrical equipment based on infrared technology according to claim 1 is characterized in that: The method for obtaining the initial prediction state matrix includes: For any set of environmental states, the sum of the preset device temperature value and the influencing factors of all environmental factors under the set of environmental states is taken as the theoretical device temperature value corresponding to the set of environmental states; Based on the element values ​​in the target matrix and the theoretical device temperature value, adjusting the element values ​​in the target matrix to obtain an updated value; The element values ​​at the corresponding positions of the target matrix are replaced with the updated values ​​to obtain the initial predicted state matrix of each monitoring point at the current moment.

5. The method for measuring temperature of underground mining electrical equipment based on infrared technology according to claim 4 is characterized in that: The method for obtaining the update value includes: Counting the number of moments corresponding to each set of environmental states, taking an environmental state set with a number of moments greater than a preset second number as a normal state set, and taking an environmental state set with a number of moments less than or equal to the preset second number as a special state set; in, Represents the updated value at the i-th position in the target matrix; Represents the element value at the i-th position in the target matrix; The theoretical value of the device temperature of the environmental state set corresponding to the column at the i-th position in the target matrix; Indicates the preset weight.

6. The method for measuring temperature of underground mining electrical equipment based on infrared technology according to claim 1 is characterized in that: The method for obtaining the final prediction state matrix includes: For any monitoring point, calculate the mean of the device temperature values ​​at all times in each environmental state set of the monitoring point as the average state value of the monitoring point in each environmental state set; Determine the preset neighborhood of each monitoring point on underground mining electrical equipment; In the preset neighborhood of each monitoring point, for any set of environmental states, the difference between the average state value of each monitoring point under the set of environmental states and the average state value of all neighboring monitoring points is averaged to obtain the state structure performance value of each monitoring point under the set of environmental states; Determine an adjustment factor based on the state structure performance value of each monitoring point under the environmental state set corresponding to the column where each element value in the initial prediction state matrix is ​​located, and the state structure performance value is negatively correlated with the adjustment factor; Each element value in the initial prediction state matrix is ​​replaced by the product of each element value and the corresponding adjustment factor, so as to obtain the final prediction state matrix of each monitoring point at the current moment.

7. The method for measuring temperature of underground mining electrical equipment based on infrared technology according to claim 1 is characterized in that: The method measures the temperature of underground mining electrical equipment based on the transition probability matrix at each monitoring point, the final predicted state matrix of each monitoring point at the current moment, and the environmental state set at the next moment, including: According to the set of environmental states at each monitoring point at the current moment, a corresponding row matrix is ​​extracted from the transition probability matrix as a comparison matrix; If the element value of the position where the maximum element value in the final prediction state matrix at the current moment is located in the comparison matrix is ​​greater than the preset probability threshold, an early warning is required; The element value of the environmental state set of each monitoring point at the next moment after the current moment in the corresponding column of the final prediction state matrix is ​​used as the equipment temperature value of each monitoring point on the underground mining electrical equipment at the next moment after the current moment.

8. A temperature measurement system for underground mining electrical equipment based on infrared technology, characterized in that: The method comprises a processor and a memory, wherein at least one instruction, at least one program, a code set or an instruction set is stored in the memory, and when the at least one instruction, at least one program, a code set or an instruction set is loaded and executed by the processor, the steps of a method for measuring the temperature of underground mining electrical equipment based on infrared technology as described in any one of claims 1 to 7 are implemented.

Images