A mine-used nano-scale wireless spray dust suppression power adjustment method and system

Abstract

The present invention relates to the field of industrial information and data processing technology, and specifically to a power adjustment method and system for nano-scale wireless spray dust suppression for mining. The method includes: obtaining dust concentration data at each sampling moment in different historical periods; obtaining sampling time segments by time series clustering; screening and obtaining target time segments according to the extreme point distribution and duration of dust concentration data in the sampling time segments; determining the adjustment degree of the target time segments according to the numerical distribution of dust concentration data at all sampling moments in each target time segment; and then determining the adjustment power at each sampling moment; and predicting the power of wireless spray in the current cycle according to the adjustment power at the same sampling moment in all historical periods. The present invention can set an adaptive adjustment power, avoid the problem of frequent power adjustment caused by directly adjusting the power according to the change of dust concentration data, and then affecting the service life of the wireless spray itself, and improve the sustainability and efficiency of the wireless spray.

Description

Technical Field

[0001] The invention relates to the technical field of industrial information and data processing, and in particular to a mine-used nano-level wireless spray dust suppression power adjustment method and system. Background Art

[0002] Nano-level wireless dust suppression spray for mining is usually an environmental management system used in mines and mining sites. This spray system uses nano-level particles to reduce the dust concentration in the environment. It can achieve dust reduction in the environment. However, since the dust concentration in the environment will change, using a single power cannot meet the changing usage scenarios.

[0003] In the related art, the dust concentration level in the environment is detected in real time, and then the power of the spray system is adjusted accordingly based on the dust concentration threshold. In this way, since the dust concentration changes frequently at some times in the actual mining environment of the mine, the method of adjusting the power based on the dust concentration threshold will be accompanied by frequent power changes of the wireless spray, affecting the life of the electronic components in the dust reduction spray device, and the sustainability of the wireless spray operation and the dust reduction efficiency are poor. Summary of the invention

[0004] In order to solve the technical problems in the related art that the dust concentration changes frequently at some moments in the actual mining environment of the mine, the method of adjusting the power based on the dust concentration threshold will be accompanied by frequent power changes of the wireless spray, affecting the life of the electronic components in the dust suppression spray device, and the sustainability and efficiency of the wireless spray operation are poor, the present invention provides a mine-use nano-scale wireless spray dust suppression power adjustment method and system, and the technical solutions adopted are as follows:

[0005] The present invention proposes a mine-used nano-scale wireless spray dust suppression power adjustment method and system, the method comprising:

[0006] Obtain dust concentration data at each sampling moment in different historical periods; perform time series clustering on different sampling moments based on the numerical value of dust concentration data to obtain sampling time series segments;

[0007] Determine the necessity of optimizing the sampling time segment according to the extreme point distribution of the dust concentration data in each sampling time segment and the duration of the sampling time segment; and select the target time segment to be optimized for power adjustment from the sampling time segment according to the necessity of optimization;

[0008] Determine the first adjustment coefficient according to the numerical discreteness of the dust concentration data at all sampling moments in each target time segment; determine the second adjustment coefficient according to the dust concentration data at the two closest sampling moments in the target time segment; determine the adjustment degree of the target time segment by combining the first adjustment coefficient, the second adjustment coefficient and the extreme difference of the dust concentration data at all sampling moments in the target time segment;

[0009] According to the adjustment degree of the target time sequence and the initial power of the wireless spray in the cycle, the adjustment power at each sampling moment is determined; according to the adjustment power at the same sampling moment of all historical cycles, the power of the wireless spray in the current cycle is predicted.

[0010] Furthermore, the extreme value point is an inflection point of the change in the value of the dust concentration data. The necessity of optimizing the sampling time segment is determined according to the extreme value point distribution of the dust concentration data in each sampling time segment and the duration of the sampling time segment, including:

[0011] Calculate the time series distance between the two extreme value points closest to each other as the time series extreme value difference; take the average of the time series extreme value differences of all extreme value points in the sampling time series segment as the segment extreme value difference;

[0012] The ratio of the number of extreme value points to the number of all sampling moments in the sampling time series segment is used as a fluctuation frequency coefficient;

[0013] Performing maximum and minimum normalization processing on the duration of the sampling time sequence segment to obtain a time impact weight;

[0014] The necessity of optimizing the sampling timing segment is determined based on the segment extreme value difference, the fluctuation frequency coefficient and the time impact weight, wherein the segment extreme value difference is negatively correlated with the necessity of optimizing the sampling timing segment, the fluctuation frequency coefficient and the time impact weight are positively correlated with the necessity of optimizing the sampling timing segment, and the value range of the optimization necessity is the normalized value.

[0015] Further, the step of selecting a target time segment to be subjected to power optimization adjustment from the sampling time segments according to the optimization necessity includes:

[0016] The sampling time segment whose optimization necessity is greater than a preset necessity threshold is used as the target time segment.

[0017] Furthermore, the first adjustment coefficient is determined according to the numerical discreteness of the dust concentration data at all sampling moments in each target time segment, including:

[0018] Calculate the variance of dust concentration data at all sampling moments in the target time series to obtain a concentration dispersion coefficient;

[0019] Calculate the mean of the dust concentration data at all sampling moments in the target time series segment to obtain the segment concentration mean;

[0020] A normalized value of the product of the concentration dispersion coefficient and the segment concentration mean is used as the first adjustment coefficient.

[0021] Furthermore, determining the second adjustment coefficient according to the dust concentration data at the two closest sampling moments in the target time sequence segment includes:

[0022] Calculate the absolute value of the difference between the dust concentration data at the two closest sampling times to obtain the adjacent concentration difference;

[0023] The mean values ​​of adjacent concentration differences corresponding to all sampling moments in the target time series are normalized and used as the second adjustment coefficient.

[0024] Further, the step of combining the first adjustment coefficient, the second adjustment coefficient and the range of dust concentration data at all sampling moments in the target time sequence to determine the adjustment degree of the target time sequence includes:

[0025] The range between the maximum and minimum values ​​of the dust concentration data at all sampling moments in the target time series is normalized and used as the range coefficient;

[0026] A normalized value of the product of the first adjustment coefficient, the second adjustment coefficient and the range coefficient is calculated to obtain an adjustment degree of the target time segment.

[0027] Further, the adjusting power at each sampling moment is determined according to the adjustment degree of the target time sequence and the initial power of the wireless spray within the period, including:

[0028] Calculate the product of the adjustment degree of any target time segment and the initial power of the wireless spray in the period to obtain the growth power, and use the sum of the growth power and the initial power as the adjustment power at the sampling moment in the corresponding target time segment;

[0029] The sampling time segments except the target time segment in the historical period are regarded as normal time segments, and the adjusted power at the sampling moment in the normal time segment is the initial power.

[0030] Furthermore, the power prediction of the wireless spray in the current cycle is performed based on the adjusted power at the same sampling moment in all historical cycles, including:

[0031] Take any sampling moment of the current period as the prediction moment, and take the moments in all historical periods with the same time sequence position as the prediction moment as the comparison moment;

[0032] The average of the adjusted powers at all comparison moments is calculated as the predicted power at the prediction moment, thereby determining the predicted power at all sampling moments in the current cycle.

[0033] Furthermore, the time series clustering of different sampling moments based on the numerical value of the dust concentration data to obtain the sampling time series segments includes:

[0034] Based on the ISODATA algorithm, cluster analysis is performed on the values ​​of dust concentration data at all sampling moments, and a historical period is divided into at least two sampling time series segments.

[0035] The present invention also proposes a power adjustment system for nano-scale wireless spray dust suppression for mining, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the power adjustment method for nano-scale wireless spray dust suppression for mining as described above when executing the computer program.

[0036] The present invention has the following beneficial effects:

[0037] The present invention obtains dust concentration data at each sampling moment in different historical periods, and then clusters the dust concentration data according to the numerical value to determine the sampling time segment. By analyzing the sampling data, it is avoided to directly analyze according to the sampling moment, which leads to frequent power changes and further affects the use time limit of the wireless sprayer. At the same time, by analyzing the sampling time segment, adjacent moments with the same and similar dust concentration data can be clustered to achieve power adjustment of the same category, thereby ensuring that the overall power change is more stable, and the power adjustment can effectively fit the actual dust concentration fluctuation situation; the necessity of optimization is determined based on the extreme point distribution of the dust concentration data and the duration of the sampling time segment, and the target time segment is obtained by screening according to the necessity of optimization. The target time segment is a time segment with more intense and frequent data fluctuations. Therefore, the power of the target time segment is adjusted. According to the numerical distribution of the dust concentration data in the target time segment, the adjustment degree of the target time segment is determined, and then the adjustment power is determined according to the adjustment degree. Thus, the adjusted power of each sampling time segment is obtained, and the power of the wireless spray in the current cycle is predicted based on the adjusted power of different historical cycles. Since the current cycle is analyzed in combination with multiple cycles, the power of the current cycle can be effectively predicted and adjusted. At the same time, by analyzing and setting the adaptive adjustment power, it is avoided that the power adjustment is made frequently according to the change of dust concentration data, which affects the service life of the wireless spray itself, and improves the sustainability and efficiency of the wireless spray. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] 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.

[0039] Figure 1 A flow chart of a method for adjusting power of nano-scale wireless spray dust suppression for mining provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] 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 power adjustment method and system of nano-scale wireless spray dust reduction for mining proposed by the present invention, its specific implementation method, structure, characteristics and effects, 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.

[0041] 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.

[0042] The specific scheme of the power adjustment method of nano-scale wireless spray dust suppression for mining provided by the present invention is described in detail below with reference to the accompanying drawings.

[0043] See also Figure 1 , which shows a flow chart of a method for adjusting power of nano-scale wireless spray dust suppression for mining provided by an embodiment of the present invention, the method comprising:

[0044] S101: Obtain dust concentration data at each sampling moment in different historical periods; perform time series clustering on different sampling moments based on the numerical values ​​of the dust concentration data to obtain sampling time series segments.

[0045] A specific implementation scenario of the present invention is to analyze the spraying power of the nano-scale wireless spray for mining. It should be noted that the spraying power of the nano-scale wireless spray for mining is usually adjusted according to the dust concentration at the current moment. When the dust concentration is large, the corresponding wireless spray power becomes larger, and when the dust concentration is small, the corresponding wireless spray power becomes smaller. Thus, adaptive dust reduction treatment is performed. However, in this way, due to the diversity of scenes, the dust concentration may change drastically many times within a certain period of time. In this case, the power of the wireless spray will also follow with large and frequent changes. Frequent power changes will lead to a large amount of unnecessary energy consumption and affect the life of electronic components in the wireless spray. Therefore, it is necessary to predict the next moment and realize orderly adjustment of the wireless spray power according to the prediction results, so that the dust concentration can be reasonably controlled while avoiding frequent changes.

[0046] Among them, the historical cycle can be a corresponding preset cycle. In the embodiment of the present invention, one day can be used as a cycle and sampling can be performed every 10 minutes. Of course, in other embodiments of the present invention, the historical cycle and the sampling time can be adjusted according to actual detection needs, and there is no limitation on this.

[0047] For example, the present invention can be applied to mine road scenarios. Since the dust on mine roads is mainly environmental dust and dust from passing vehicles, and the traffic volume varies greatly in different time periods, but the traffic volume is similar at the same time of each day, the present invention can be based on this, taking the previous few days as a historical period, and counting the dust concentration data of each day at each sampling time, so as to analyze today's dust concentration and realize wireless spray power control.

[0048] Among them, the acquisition of dust concentration data in the environment can use corresponding detection equipment, and there is no restriction on this.

[0049] Furthermore, in some embodiments of the present invention, time series clustering is performed on different sampling moments based on the numerical value of dust concentration data to obtain sampling time segments, including: based on the ISODATA algorithm, clustering analysis is performed on the numerical values ​​of dust concentration data at all sampling moments, and a historical period is divided into at least two sampling time segments.

[0050] Among them, the ISODATA algorithm is a clustering algorithm well known in the art. Based on the ISODATA algorithm, the dust concentration data at all sampling moments in a historical period can be clustered and analyzed.

[0051] It can be understood that since the divided sampling time segments are data segments that are continuous in time series, the embodiment of the present invention can construct a coordinate system with the sampling time as the horizontal axis and the dust concentration data as the vertical axis, and mark the dust concentration data at each sampling time with coordinate points in the coordinate system, and perform cluster analysis based on this, so that each sampling time segment has a continuous time series effect.

[0052] In the embodiment of the present invention, each sampling time segment represents an area that is continuous in time series and has relatively similar dust concentration data fluctuations. Since the factors affecting dust concentration in different time periods vary greatly, each historical period can be effectively divided into different time periods with similar dust concentrations.

[0053] S102: Determine the necessity of optimizing the sampling time segment according to the extreme point distribution of the dust concentration data in each sampling time segment and the duration of the sampling time segment; and select the target time segment to be subjected to power optimization adjustment from the sampling time segment according to the necessity of optimization.

[0054] Among them, the extreme point is the inflection point of the numerical change of the dust concentration data. Since the dust concentration change has an increasing trend and a decreasing area, when the increasing trend changes to a decreasing trend, or the decreasing trend changes to an increasing trend, the corresponding inflection point is the extreme point.

[0055] Furthermore, in some embodiments of the present invention, the necessity of optimizing the sampling time segment is determined based on the extreme point distribution of the dust concentration data in each sampling time segment and the duration of the sampling time segment, including: calculating the time series distance between the two nearest extreme points as the time series extreme value difference; taking the average of the time series extreme value differences of all extreme points in the sampling time segment as the segment extreme value difference; taking the ratio of the number of extreme points to the number of all sampling moments in the sampling time segment as the frequent fluctuation coefficient; performing maximum and minimum value normalization processing on the duration of the sampling time segment to obtain the time impact weight; determining the necessity of optimizing the sampling time segment based on the segment extreme value difference, the frequent fluctuation coefficient and the time impact weight, wherein the segment extreme value difference is negatively correlated with the necessity of optimizing the sampling time segment, the frequent fluctuation coefficient and the time impact weight are positively correlated with the necessity of optimizing the sampling time segment, and the value range of the optimization necessity is the normalized value.

[0056] Among them, the two extreme value points closest to each other, that is, the two extreme value points adjacent to each other at the sampling moment in the time series, have a complete time series segment with the same trend change between the two extreme value points, and the duration of the time series segment is the time series extreme value difference. Then, the average of the time series extreme value differences of all extreme value points in the sampling time series segment is taken as the segment extreme value difference. The larger the segment extreme value difference, the larger the time series distance between the corresponding two adjacent extreme value points.

[0057] Among them, the ratio of the number of extreme points to the number of all sampling moments in the sampling time segment is taken as the fluctuation frequency coefficient. The larger the fluctuation frequency coefficient is, the larger the proportion of the corresponding extreme points is, that is, the more frequent the corresponding data fluctuations in the sampling time segment are.

[0058] Among them, the duration of the sampling time segment is normalized to the maximum and minimum values ​​to obtain the time impact weight, which is also the weight coefficient corresponding to the sampling time segment. The longer the duration of the sampling time segment, the larger the value of the time impact weight, the higher the corresponding weight, and the more effective regulation is needed.

[0059] Therefore, combined with the above analysis, the necessity of optimization is determined by combining the segment extreme value difference, fluctuation frequency coefficient and time impact weight.

[0060] In one embodiment of the present invention, the normalization processing can be specifically, for example, maximum and minimum value normalization processing, and the normalization in subsequent steps can all adopt maximum and minimum value normalization processing. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of numerical values, which will not be described in detail.

[0061] Among them, a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplication relationship, an addition relationship, or the power of an exponential function, which is determined by actual application; a negative correlation means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by actual application.

[0062] In an embodiment of the present invention, the sum of the segment extreme value difference and a non-zero constant can be used as the denominator, and the product of the fluctuation frequency coefficient and the time impact weight can be used as the numerator. The fractional calculation and normalization can be performed to obtain the optimization necessity. Alternatively, the negative number of the segment extreme value difference can be calculated, normalized to obtain the segment extreme value index, and the product of the segment extreme value index, the fluctuation frequency coefficient and the time impact weight can be calculated and normalized to obtain the optimization necessity. There is no limitation on this.

[0063] The necessity of optimization in the embodiment of the present invention represents the degree of necessity for spray power optimization in the sampling time segment. The greater the necessity of optimization, the more drastic the timing fluctuation in the corresponding sampling time segment and the longer the duration, the more power optimization is needed to ensure the dust reduction effect.

[0064] Furthermore, in some embodiments of the present invention, a target time segment to be subjected to power optimization adjustment is screened from the sampling time segments according to the optimization necessity, including: taking the sampling time segment whose optimization necessity is greater than a preset necessity threshold as the target time segment.

[0065] Among them, the preset necessity threshold is the threshold value of optimization necessity. Since the greater the optimization necessity, the more severe the timing fluctuation in the corresponding sampling timing segment and the longer the duration, the more power optimization is needed. The preset necessity threshold in the embodiment of the present invention can be specifically 0.85, for example. When the optimization necessity is greater than 0.85, the corresponding sampling timing segment is used as the target timing segment, and the target timing segment is the timing segment that needs power optimization.

[0066] After obtaining the target time segment to be optimized by screening the fluctuation of the data in each sampling time segment, power analysis can be performed according to the specific dust concentration change in the target time segment. The analysis process is shown in the subsequent embodiments.

[0067] S103: Determine a first adjustment coefficient based on the numerical discreteness of the dust concentration data at all sampling moments in each target time segment; determine a second adjustment coefficient based on the dust concentration data at the two closest sampling moments in the target time segment; and determine the degree of adjustment of the target time segment by combining the first adjustment coefficient, the second adjustment coefficient, and the extreme value of the dust concentration data at all sampling moments in the target time segment.

[0068] In the embodiment of the present invention, the power adjustment effect can be determined by combining the numerical analysis of the dust concentration data at all sampling moments in the target time sequence.

[0069] Furthermore, in some embodiments of the present invention, a first adjustment coefficient is determined based on the numerical discreteness of the dust concentration data at all sampling moments in each target time segment, including: calculating the variance of the dust concentration data at all sampling moments in the target time segment to obtain a concentration dispersion coefficient; calculating the mean of the dust concentration data at all sampling moments in the target time segment to obtain a segment concentration mean; and taking the normalized value of the product of the concentration dispersion coefficient and the segment concentration mean as the first adjustment coefficient.

[0070] In the embodiment of the present invention, the larger the discreteness, the more drastic the numerical fluctuation of the dust concentration data at all sampling moments in the corresponding target time segment, and the power needs to be increased to avoid affecting the dust reduction effect when the dust concentration value fluctuates to a large value. Therefore, the discreteness is determined by variance calculation to obtain the concentration dispersion coefficient.

[0071] In the embodiment of the present invention, the larger the value of the dust concentration data in the target time segment is, the more power needs to be increased, thereby calculating the average of the dust concentration data at all sampling moments in the target time segment to obtain the segment concentration average.

[0072] Combine the concentration dispersion coefficient and the segment concentration mean, and use the normalized value of the corresponding product as the first adjustment coefficient. The larger the first adjustment coefficient, the greater the fluctuation of the dust concentration data in the target time series segment, and the higher the overall concentration.

[0073] Furthermore, in some embodiments of the present invention, a second adjustment coefficient is determined based on dust concentration data at two sampling moments closest to each other in a target time segment, including: calculating the absolute value of the difference between the dust concentration data at two sampling moments closest to each other to obtain adjacent concentration differences; and normalizing the mean of adjacent concentration differences corresponding to all sampling moments in the target time segment as the second adjustment coefficient.

[0074] Among them, the dust concentration data at the two closest sampling moments, that is, the dust concentration data at the two adjacent sampling moments in time series, and the absolute value of the data difference between them represent the change of dust concentration at the two sampling moments. The mean of the adjacent concentration differences corresponding to all sampling moments in the target time series segment is normalized as the second adjustment coefficient. The second adjustment coefficient represents the numerical fluctuation at the sampling moment level. The larger the second adjustment coefficient, the greater the dust concentration change at the adjacent sampling moments. Therefore, the dust concentration fluctuation stability in the target time period is worse.

[0075] Furthermore, in some embodiments of the present invention, the adjustment degree of the target time segment is determined in combination with the first adjustment coefficient, the second adjustment coefficient and the range of the dust concentration data at all sampling moments in the target time segment, including: normalizing the range of the maximum and minimum values ​​of the dust concentration data at all sampling moments in the target time segment as the range coefficient; calculating the normalized value of the product of the first adjustment coefficient, the second adjustment coefficient and the range coefficient to obtain the adjustment degree of the target time segment.

[0076] Among them, the larger the first adjustment coefficient, the greater the fluctuation of the dust concentration data in the target time segment, and the higher the overall dust concentration, while the larger the second adjustment coefficient, the greater the dust concentration change between adjacent sampling moments, the worse the dust concentration fluctuation stability, and thus, the more power needs to be increased to ensure the dust reduction effect. Among them, the range reflects the maximum fluctuation range of the dust concentration data. If the range is larger, it means that there is a greater data fluctuation in the target time segment, and the corresponding adjustment degree is also greater.

[0077] Therefore, the present invention calculates the normalized value of the product of the first adjustment coefficient, the second adjustment coefficient and the range coefficient to obtain the adjustment degree of the target time segment. The greater the adjustment degree, the more it is necessary to increase the corresponding wireless spray power to ensure the reliability of the adjustment.

[0078] S104: Determine the adjusted power at each sampling moment according to the adjustment degree of the target time sequence and the initial power of the wireless spray in the cycle; and predict the power of the wireless spray in the current cycle according to the adjusted power at the same sampling moment in all historical cycles.

[0079] Furthermore, in some embodiments of the present invention, the adjusted power at each sampling moment is determined according to the adjustment degree of the target time segment and the initial power of the wireless spray within the cycle, including: calculating the product of the adjustment degree of any target time segment and the initial power of the wireless spray within the cycle to obtain the growth power, and taking the sum of the growth power and the initial power as the adjusted power at the sampling moment in the corresponding target time segment; taking the sampling time segments other than the target time segments in the historical cycle as normal time segments, and the adjusted power at the sampling moment in the normal time segments as the initial power.

[0080] Among them, since the greater the adjustment degree, the more the power of the wireless spray needs to be increased, the present invention calculates the product of the adjustment degree of the target time segment and the initial power of the wireless spray in the cycle to obtain the increased power. Among them, the initial power of the wireless spray in the cycle is also the preset standard power, and each wireless spray has a corresponding standard power at the beginning of operation, which may be the rated power of the wireless spray itself, or it may be a preset power value, and there is no limitation on this.

[0081] The growth power in the embodiment of the present invention is the power that needs to be adjusted and increased. The present invention uses the sum of the growth power and the initial power as the adjusted power at the sampling moment in the corresponding target time segment. The adjusted power is the power that the target time segment needs to be adjusted to after analysis. The dust reduction effect is optimal when the target time segment runs under the adjusted power, and frequent power fluctuations are avoided for the target time segment with more frequent fluctuations, further protecting the operating state of the wireless spray itself.

[0082] Among them, the sampling time segments other than the target time segment in the historical period are time segments with small corresponding value changes and slow dust concentration data fluctuations, which can be processed using standard power. The sampling time segments other than the target time segment in the historical period are regarded as normal time segments, and the adjusted power at the sampling moment in the normal time segment is the initial power. Thus, the adjusted power of each sampling time segment is obtained.

[0083] Furthermore, in some embodiments of the present invention, the power of wireless spray in the current cycle is predicted based on the adjusted power at the same sampling moment in all historical cycles, including: taking any sampling moment in the current cycle as the prediction moment, and taking the moment in all historical cycles with the same time sequence position as the prediction moment as the comparison moment; calculating the average of the adjusted power at all comparison moments as the predicted power at the prediction moment, thereby determining the predicted power of all sampling moments in the current cycle.

[0084] In the embodiment of the present invention, since multiple historical cycles are analyzed and since the dust concentration change has similar effects in different cycles, the embodiment of the present invention can analyze the dust concentration of the current cycle based on all historical cycles, thereby determining the spray power at each sampling moment in the current cycle.

[0085] Among them, the moments with the same time sequence position as the predicted moment in all historical periods are taken as comparison moments. That is to say, when a historical period is 1 day, the present invention can take the moments with the same time sequence as the predicted moment in each historical day as comparison moments. Of course, the historical period can also be a week, a year, etc., and the predicted moment and the comparison moment will be adjusted accordingly.

[0086] In an embodiment of the present invention, the predicted moment can be analyzed in combination with the adjusted powers of all comparison moments, that is, the average of the adjusted powers of all comparison moments is calculated as the predicted power of the predicted moment. In this way, the predicted powers of all sampling moments in the current cycle can be analyzed.

[0087] In other embodiments of the present invention, the power fluctuation of the current cycle may be analyzed according to the fluctuation of the adjusted power at different sampling moments in the dust concentration data of all historical cycles, and then the predicted power at different sampling moments of the current cycle may be determined.

[0088] The present invention obtains dust concentration data at each sampling moment in different historical periods, and then clusters the dust concentration data according to the numerical value to determine the sampling time segment. By analyzing the sampling data, it is avoided to directly analyze according to the sampling moment, which leads to frequent power changes and further affects the use time limit of the wireless sprayer. At the same time, by analyzing the sampling time segment, adjacent moments with the same and similar dust concentration data can be clustered to achieve power adjustment of the same category, thereby ensuring that the overall power change is more stable, and the power adjustment can effectively fit the actual dust concentration fluctuation situation; the necessity of optimization is determined based on the extreme point distribution of the dust concentration data and the duration of the sampling time segment, and the target time segment is obtained by screening according to the necessity of optimization. The target time segment is a time segment with more intense and frequent data fluctuations. Therefore, the power of the target time segment is adjusted. According to the numerical distribution of the dust concentration data in the target time segment, the adjustment degree of the target time segment is determined, and then the adjustment power is determined according to the adjustment degree. Thus, the adjusted power of each sampling time segment is obtained, and the power of the wireless spray in the current cycle is predicted based on the adjusted power of different historical cycles. Since the current cycle is analyzed in combination with multiple cycles, the power of the current cycle can be effectively predicted and adjusted. At the same time, by analyzing and setting the adaptive adjustment power, it is avoided that the power adjustment is made frequently according to the change of dust concentration data, which affects the service life of the wireless spray itself, and improves the sustainability and efficiency of the wireless spray.

[0089] On the other hand, the present invention also provides a nano-level wireless spray dust suppression power adjustment system for mining. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of a method for adjusting the power of nano-level wireless spray dust suppression for mining as described above are implemented.

[0090] 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.

[0091] 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 adjusting power of nano-scale wireless spray dust suppression for mining, characterized in that: The method comprises: Obtain dust concentration data at each sampling moment in different historical periods; perform time series clustering on different sampling moments based on the numerical value of dust concentration data to obtain sampling time series segments; Determine the necessity of optimizing the sampling time segment according to the extreme point distribution of the dust concentration data in each sampling time segment and the duration of the sampling time segment; and select the target time segment to be optimized for power adjustment from the sampling time segment according to the necessity of optimization; Determine the first adjustment coefficient according to the numerical discreteness of the dust concentration data at all sampling moments in each target time segment; determine the second adjustment coefficient according to the dust concentration data at the two closest sampling moments in the target time segment; determine the adjustment degree of the target time segment by combining the first adjustment coefficient, the second adjustment coefficient and the extreme difference of the dust concentration data at all sampling moments in the target time segment; According to the adjustment degree of the target time sequence and the initial power of the wireless spray in the cycle, the adjustment power at each sampling moment is determined; according to the adjustment power at the same sampling moment of all historical cycles, the power of the wireless spray in the current cycle is predicted; The first adjustment coefficient is determined according to the numerical discreteness of the dust concentration data at all sampling moments in each target time segment, including: Calculate the variance of dust concentration data at all sampling moments in the target time series to obtain a concentration dispersion coefficient; Calculate the mean of the dust concentration data at all sampling moments in the target time series segment to obtain the segment concentration mean; taking a normalized value of the product of the concentration dispersion coefficient and the segment concentration mean as a first adjustment coefficient; The step of determining the second adjustment coefficient according to the dust concentration data at the two closest sampling moments in the target time sequence segment includes: Calculate the absolute value of the difference between the dust concentration data at the two closest sampling times to obtain the adjacent concentration difference; Normalize the mean values ​​of the adjacent concentration differences corresponding to all sampling moments in the target time series segment to serve as the second adjustment coefficient; The step of combining the first adjustment coefficient, the second adjustment coefficient, and the range of dust concentration data at all sampling moments in the target time sequence to determine the adjustment degree of the target time sequence includes: The range between the maximum and minimum values ​​of the dust concentration data at all sampling moments in the target time series is normalized and used as the range coefficient; A normalized value of the product of the first adjustment coefficient, the second adjustment coefficient and the range coefficient is calculated to obtain an adjustment degree of the target time segment.

2. A mine-used nano-scale wireless spray dust suppression power adjustment method as claimed in claim 1, characterized in that: The extreme value point is the inflection point of the change in the value of the dust concentration data. The necessity of optimizing the sampling time sequence segment is determined according to the extreme value point distribution of the dust concentration data in each sampling time sequence segment and the duration of the sampling time sequence segment, including: Calculate the time series distance between the two extreme value points closest to each other as the time series extreme value difference; take the average of the time series extreme value differences of all extreme value points in the sampling time series segment as the segment extreme value difference; The ratio of the number of extreme value points to the number of all sampling moments in the sampling time series segment is used as a fluctuation frequency coefficient; Performing maximum and minimum normalization processing on the duration of the sampling time sequence segment to obtain a time impact weight; The necessity of optimizing the sampling timing segment is determined based on the segment extreme value difference, the fluctuation frequency coefficient and the time impact weight, wherein the segment extreme value difference is negatively correlated with the necessity of optimizing the sampling timing segment, the fluctuation frequency coefficient and the time impact weight are positively correlated with the necessity of optimizing the sampling timing segment, and the value range of the optimization necessity is the normalized value.

3. A mine-used nano-scale wireless spray dust suppression power adjustment method as claimed in claim 1, characterized in that: The step of selecting a target time segment to be subjected to power optimization adjustment from the sampling time segments according to the optimization necessity includes: The sampling time segment whose optimization necessity is greater than a preset necessity threshold is used as the target time segment.

4. A mine-used nano-scale wireless spray dust suppression power adjustment method as claimed in claim 1, characterized in that: The step of determining the adjusted power at each sampling moment according to the adjustment degree of the target time sequence and the initial power of the wireless spray within the period includes: Calculate the product of the adjustment degree of any target time segment and the initial power of the wireless spray in the period to obtain the growth power, and use the sum of the growth power and the initial power as the adjustment power at the sampling moment in the corresponding target time segment; The sampling time segments except the target time segment in the historical period are regarded as normal time segments, and the adjusted power at the sampling moment in the normal time segment is the initial power.

5. A mine-used nano-scale wireless spray dust suppression power adjustment method as claimed in claim 1, characterized in that: The power prediction of the wireless spray in the current cycle is performed based on the adjusted power at the same sampling moment in all historical cycles, including: Take any sampling moment of the current period as the prediction moment, and take the moments in all historical periods with the same time sequence position as the prediction moment as the comparison moment; The average of the adjusted powers at all comparison moments is calculated as the predicted power at the prediction moment, thereby determining the predicted power at all sampling moments in the current cycle.

6. A mine-used nano-scale wireless spray dust suppression power adjustment method as claimed in claim 1, characterized in that: The time series clustering of different sampling moments based on the numerical value of the dust concentration data to obtain the sampling time series segment includes: Based on the ISODATA algorithm, cluster analysis is performed on the values ​​of dust concentration data at all sampling moments, and a historical period is divided into at least two sampling time series segments.

7. A nanometer-level wireless spray dust suppression power adjustment system for mining, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

Images