CN104464232A - Forecasting and early warning detection model in emulsion explosive production technological process based on danger source - Google Patents

Forecasting and early warning detection model in emulsion explosive production technological process based on danger source Download PDF

Info

Publication number
CN104464232A
CN104464232A CN201410735325.4A CN201410735325A CN104464232A CN 104464232 A CN104464232 A CN 104464232A CN 201410735325 A CN201410735325 A CN 201410735325A CN 104464232 A CN104464232 A CN 104464232A
Authority
CN
China
Prior art keywords
parameter
value
prediction
matter sources
dangerous matter
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201410735325.4A
Other languages
Chinese (zh)
Other versions
CN104464232B (en
Inventor
吴怀广
黄志平
时清海
陈金德
付金华
李国亮
邓水朋
徐建辉
温文伟
杨焱华
李文波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Four O One Factory Co ltd
Guangdong Zhensheng Technology Group Co ltd
Zhengzhou University of Light Industry
Original Assignee
Guangdong No401 Factory
GUANGDONG ZHENSHENG PACKAGING TECHNOLOGY CO LTD
Zhengzhou University of Light Industry
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong No401 Factory, GUANGDONG ZHENSHENG PACKAGING TECHNOLOGY CO LTD, Zhengzhou University of Light Industry filed Critical Guangdong No401 Factory
Priority to CN201410735325.4A priority Critical patent/CN104464232B/en
Publication of CN104464232A publication Critical patent/CN104464232A/en
Application granted granted Critical
Publication of CN104464232B publication Critical patent/CN104464232B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Emergency Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • General Factory Administration (AREA)

Abstract

The invention discloses a forecasting and early warning detection model in an emulsion explosive production technological process based on a danger source, and belongs to the technical field of danger source forecasting and early warning in the civil explosive industry. The forecasting and early warning detection model is technically characterized in that a danger source forecasting and early warning value is built, wherein the forecasting and early warning value of a danger source parameter of emulsion explosive production technology equipment is built; danger source parameter change fluctuation is measured; the danger source parameter correlation is described; a production line forecasting and early warning statistic analysis strategy is built. The forecasting and early warning detection model in the emulsion explosive production technological process based on the danger source is convenient to operate and effective, and is used for modeling for forecasting and early warning detection in the emulsion explosive production process.

Description

乳化炸药生产工艺过程中基于危险源的预测预警检测模型Prediction, early warning and detection model based on hazard sources in the production process of emulsion explosives

技术领域technical field

本发明涉及一种预测预警检测模型,更具体地说,尤其涉及一种乳化炸药生产工艺过程中基于危险源参数的预测预警检测模型。The invention relates to a prediction, early warning and detection model, more specifically, to a prediction, early warning and detection model based on hazard source parameters in the production process of emulsion explosives.

背景技术Background technique

现有的乳化炸药生产线对危险源(生产设备)只是设置达到生产线高危死锁的阈值。对于在阈值范围内的幅度波动没有进行很好的实时处理、统计分析,而仅是通过控制室的操作人员值守来发现处理问题。The existing emulsion explosive production line only sets the threshold for the dangerous source (production equipment) to reach the high-risk deadlock of the production line. There is no real-time processing and statistical analysis for the amplitude fluctuations within the threshold range, but only the operators in the control room are on duty to find processing problems.

发明内容Contents of the invention

本发明的目的在于针对上述现有技术的不足,提供一种使用方便、预测预警较为准确且使用效果良好的乳化炸药生产工艺过程中基于危险源的预测预警检测模型。The object of the present invention is to address the shortcomings of the above-mentioned prior art, and provide a prediction, early warning and detection model based on hazard sources in the production process of emulsion explosives that is easy to use, accurate in prediction and early warning, and good in use.

本发明的技术方案是这样实现的:一种乳化炸药生产工艺过程中基于危险源的预测预警检测模型,该模型包括下述四部分:The technical solution of the present invention is realized in this way: a kind of prediction and early warning detection model based on hazard source in the emulsion explosive production process, this model comprises following four parts:

(1)建立危险源预测预警值:建立基于乳化炸药生产工艺设备参数阈值的各个危险源预测预警值;所述设备参数阈值,是指当生产设备达到参数阈值后整个生产线死锁、停止生产;所述危险源预测预警值小于对应的设备参数阈值;(1) Establish hazard prediction and early warning value: establish each hazard prediction and early warning value based on the emulsion explosive production process equipment parameter threshold; the equipment parameter threshold refers to deadlock and stop production of the entire production line when the production equipment reaches the parameter threshold; The hazard prediction and early warning value is less than the corresponding device parameter threshold;

(2)危险源参数值波动度量:当生产线设备的参数值达到或超出相关危险源预测预警值时,利用相邻两个时间间隔所确定直线的斜率作为危险源参数波动值的变化率,危险源参数值的变化率用作预测预警响应机制的等级依据以及危险源设备潜在不稳定因素检测的依据;(2) Fluctuation measurement of hazard parameter values: When the parameter values of the production line equipment reach or exceed the predicted warning value of the relevant hazard source, the slope of the straight line determined by two adjacent time intervals is used as the change rate of the hazard parameter fluctuation value. The rate of change of source parameter values is used as the basis for predicting the level of the early warning response mechanism and the basis for detecting potential instability factors of hazardous source equipment;

(3)刻画危险源参数相关性:当某个危险源参数超出预测预警值时,通过相对坐标复合的方法,将各个参数复合在一起,同一时刻上超出预测预警值的参数均用红色标注,未超出预测预警值的参数则用黑色标注;同一时刻参数标注形成一个格局,每一个格局中的红色标注个数称为格局的相关度;如果格局中所有的参数值都是红色标注则称为一个完全相关性格局;反之,如果格局中所有的参数值都为黑色标注则称为一个非相关性格局;通过格局对危险源参数相关性的刻画可以直观有效的了解乳化炸药生产线各个危险源之间变化的相互影响,进而可以考虑相关的处置措施;(3) Characterize the correlation of hazard source parameters: when a hazard source parameter exceeds the predicted warning value, the parameters are compounded together through the method of relative coordinate compounding, and the parameters exceeding the predicted warning value at the same time are marked in red. The parameters that do not exceed the predicted warning value are marked in black; the parameters marked at the same time form a pattern, and the number of red marks in each pattern is called the correlation degree of the pattern; if all the parameter values in the pattern are marked in red, it is called A complete correlation pattern; on the contrary, if all the parameter values in the pattern are marked in black, it is called a non-correlation pattern; by describing the correlation of hazard parameters in the pattern, it is possible to intuitively and effectively understand the relationship between each hazard of the emulsion explosive production line. Interactions between changes, and then relevant disposal measures can be considered;

(4)生产线预测预警统计分析策略:采用粗糙集理论中的关联规则、概率统计中的期望与方差理论对每周、每月乃至更长时段的生产线上预测预警次数进行统计评估分析;本模型只强调生产线预测预警次数的统计分析这种策略,适用与各个危险源参数。(4) Statistical analysis strategy for production line prediction and early warning: use the association rules in rough set theory and the expectation and variance theory in probability statistics to conduct statistical evaluation and analysis on the number of prediction and early warning times on the production line on a weekly, monthly or longer basis; this model The strategy of only emphasizing the statistical analysis of production line prediction and early warning times is applicable to each hazard parameter.

上述的乳化炸药生产工艺过程中基于危险源的预测预警检测模型中,步骤(1)所述危险源预测预警值是根据正常生产情况下生产设备各个参数值划定的较小的波动范围。In the above-mentioned emulsion explosive production process based on the hazard source prediction and early warning detection model, the hazard source prediction and early warning value in step (1) is a small fluctuation range delineated according to each parameter value of the production equipment under normal production conditions.

上述的乳化炸药生产工艺过程中基于危险源的预测预警检测模型中,步骤(2)所述变化率公式为:k=(y2-y1)/(x2-x1);其中:当设备参数值高于危险源预测预警值上界时,危险源参数波动值的变化率为正,直线的斜率越大说明危险源参数波动值的变化率越大;当设备参数值低于危险源预测预警值下界时,危险源参数波动值的变化率为负值,直线的斜率越小说明危险源参数波动值的变化率越大。In the above-mentioned emulsion explosive production process based on the hazard source prediction and early warning detection model, the rate of change formula in step (2) is: k=(y 2 -y 1 )/(x 2 -x 1 ); where: when When the equipment parameter value is higher than the upper limit of the hazard prediction and warning value, the change rate of the hazard parameter fluctuation value is positive, and the larger the slope of the straight line, the greater the change rate of the hazard parameter fluctuation value; when the equipment parameter value is lower than the hazard source When predicting the lower bound of the warning value, the change rate of the hazard parameter fluctuation value is negative, and the smaller the slope of the straight line, the greater the change rate of the hazard parameter fluctuation value.

上述的乳化炸药生产工艺过程中基于危险源的预测预警检测模型中,步骤(4)所述的对每周、每月乃至更长时段的生产线上预测预警次数进行统计评估分析,并不给出具体每个危险源参数预测预警次数统计分析所用到的具体方法,这要根据实际应用场景来确定适用粗糙集理论中的关联规则或概率统计中的期望与方差理论。In the above-mentioned emulsion explosive production process based on the hazard source prediction and early warning detection model, the statistical evaluation and analysis of the number of weekly, monthly or even longer production line prediction and early warning described in step (4) is not given. Specifically, the specific method used in the statistical analysis of the forecast and warning times of each hazard parameter depends on the actual application scenario to determine the application of the association rules in rough set theory or the expectation and variance theory in probability statistics.

本发明采用上述模型结构后,在将危险源各个参数可以实时检测提取的基础上,利用本发明模型可以实时的发现危险源信号的异常波动。实时地根据异常波动的变化率来采取不同的应急处理策略;利用大数据的存储分析技术对统计每周、每月乃至更长时间范围的预测预警次数进行统计分析;对于生产线上单个危险源参数发生变化时对其它危险源参数的影响则通过参数变化格局的方法实现,以达到实时检测危险源参数相关性的目的。After the present invention adopts the above model structure, on the basis of real-time detection and extraction of various parameters of the danger source, the abnormal fluctuation of the danger source signal can be found in real time by using the model of the present invention. Adopt different emergency response strategies in real time according to the rate of change of abnormal fluctuations; use big data storage analysis technology to statistically analyze the number of predictions and early warnings in a weekly, monthly or even longer time range; for a single hazard parameter on the production line The impact on other hazard parameters when changes occur is realized through the method of parameter change pattern, so as to achieve the purpose of real-time detection of the correlation of hazard parameters.

附图说明Description of drawings

下面结合附图中的实施例对本发明作详细地说明,但并不构成对本发明的任何限制。The present invention will be described in detail below in conjunction with the embodiments in the accompanying drawings, but this does not constitute any limitation to the present invention.

图1是本发明的生产线危险源预测预警示意图;Fig. 1 is a schematic diagram of the production line danger source prediction and early warning of the present invention;

图中:1为生产线自锁阈值;2为生产预期值;3为预设预测预警值;4为生产实际值。In the figure: 1 is the self-locking threshold of the production line; 2 is the production expected value; 3 is the preset forecast and early warning value; 4 is the actual production value.

图2是本发明的危险源超出预测预警的变化率示意图;Fig. 2 is a schematic diagram of the rate of change of the danger source of the present invention beyond the predicted warning;

图中:1是生产线自锁阈值;2为生产预期值;3为预设预测预警值;5为变化率。In the figure: 1 is the self-locking threshold of the production line; 2 is the expected production value; 3 is the preset forecast and early warning value; 5 is the rate of change.

图3是本发明危险源预测预警次数统计的示意图;Fig. 3 is a schematic diagram of the number of times of hazard prediction and early warning of the present invention;

图中:位于X轴上的黑圆点为生产无预测预警;位于X轴和Y轴之间的红圆点为预测预警次数。In the figure: the black dots on the X-axis are production forecast warnings; the red dots between the X-axis and Y-axis are the number of forecast warnings.

图4是本发明危险源预警关联性格局的示意图。Fig. 4 is a schematic diagram of the correlation pattern of early warning of hazard sources in the present invention.

图中:6为生产正常值;7为各参数正常生产中值;8为各参数预警值界值;9为预测预警值。In the figure: 6 is the normal value of production; 7 is the median value of normal production of each parameter; 8 is the boundary value of early warning value of each parameter; 9 is the predicted early warning value.

具体实施方式Detailed ways

参阅图1至图4所示,本发明的一种乳化炸药生产工艺过程中基于危险源的预测预警检测模型,该模型包括下述四部分:Referring to Fig. 1 to shown in Fig. 4, in a kind of emulsion explosive production technology process of the present invention, based on the prediction early warning detection model of hazard source, this model comprises following four parts:

(1)建立危险源预测预警值:建立基于乳化炸药生产工艺设备参数阈值的各个危险源预测预警值;所述设备参数阈值,是指当生产设备达到参数阈值后整个生产线死锁、停止生产;所述危险源预测预警值小于对应的设备参数阈值;所述危险源预测预警值是根据正常生产情况下生产设备各个参数值划定的较小的波动范围。如图1所示,x轴坐标为时间t,y轴坐标是不同的危险源参数,取值单位不同,该模型作为抽象模型只是给出相关规定,而不具体设定。图中生产线自锁阈值1由生产线设备厂家给出的;生产预期值2则是生产过程中的均值线,要根据实际情况确定;预设预测预警值3则分为预测预警值上界和预测预警值下界,分别位于生产预期值的上下方。生产实际值4则是指实际检测到的参数值,该值可以时直线、曲线,图中只是说明参数的实际值可能存在波动的示意。(1) Establish hazard prediction and early warning value: establish each hazard prediction and early warning value based on the emulsion explosive production process equipment parameter threshold; the equipment parameter threshold refers to deadlock and stop production of the entire production line when the production equipment reaches the parameter threshold; The hazard source prediction and early warning value is less than the corresponding equipment parameter threshold; the hazard source prediction and early warning value is a small fluctuation range defined according to each parameter value of the production equipment under normal production conditions. As shown in Figure 1, the x-axis coordinates are time t, and the y-axis coordinates are different hazard source parameters with different value units. As an abstract model, this model only provides relevant regulations without specific settings. In the figure, the production line self-locking threshold 1 is given by the production line equipment manufacturer; the production expected value 2 is the mean line in the production process, which should be determined according to the actual situation; the preset forecast warning value 3 is divided into the upper bound of the forecast warning value and the forecast The lower bounds of the early warning value are respectively located above and below the expected production value. The actual production value 4 refers to the actual detected parameter value, which can be a straight line or a curve, and the figure only shows that the actual value of the parameter may fluctuate.

(2)危险源参数值波动度量:当生产线设备的参数值达到或超出相关危险源预测预警值时,利用相邻两个时间间隔所确定直线的斜率作为危险源参数波动值的变化率,变化率公式为:k=(y2-y1)/(x2-x1);其中:当设备参数值高于危险源预测预警值上界时,危险源参数波动值的变化率为正,直线的斜率越大说明危险源参数波动值的变化率越大;当设备参数值低于危险源预测预警值下界时,危险源参数波动值的变化率为负值,直线的斜率越小说明危险源参数波动值的变化率越大。危险源参数值的变化率用作预测预警响应机制的等级依据以及危险源设备潜在不稳定因素检测的依据;如图2所示,图中除了图1中介绍的x轴、y轴,生产线自锁阈值1、生产预期值2以及预设预测预警值3三线外,就是当危险源参数超出预测预警值时规定时间间隔内参数值的变化率5。x1,x2分别表示危险源参数运行在正常范围和预测预警范围的时刻。至于当危险源参数超过预测预警值上界或下界时,即x2时刻,前一时刻x1的取值则根据不同参数进行设定。(2) Fluctuation measurement of hazard parameter values: When the parameter values of the production line equipment reach or exceed the predicted warning value of the relevant hazard source, the slope of the straight line determined by two adjacent time intervals is used as the rate of change of the hazard parameter fluctuation value. The rate formula is: k=(y 2 -y 1 )/(x 2 -x 1 ); where: when the equipment parameter value is higher than the upper limit of the hazard prediction and early warning value, the change rate of the hazard parameter fluctuation value is positive, The larger the slope of the straight line, the greater the change rate of the hazard parameter fluctuation value; when the equipment parameter value is lower than the lower limit of the hazard prediction and warning value, the change rate of the hazard parameter fluctuation value is negative, and the smaller the slope of the straight line, the danger The greater the rate of change of the source parameter fluctuation value. The change rate of the hazard parameter value is used as the basis for predicting the level of the early warning response mechanism and the basis for detecting potential instability factors of the hazard equipment; as shown in Figure 2, in addition to the x-axis and y-axis introduced in Figure 1, the production line automatically Lock threshold 1, production expected value 2, and preset forecast warning value 3 are outside the third line, that is, when the hazard source parameter exceeds the forecast warning value, the change rate 5 of the parameter value within the specified time interval. x 1 and x 2 represent the moment when the hazard source parameters are running in the normal range and the forecast and warning range respectively. As for when the hazard source parameter exceeds the upper or lower bound of the predicted warning value, that is, at the moment x2 , the value of x1 at the previous moment is set according to different parameters.

(3)刻画危险源参数相关性:当某个危险源参数超出预测预警值时,通过相对坐标复合的方法,将各个参数复合在一起,同一时刻上超出预测预警值的参数均用红色标注,未超出预测预警值的参数则用黑色标注;同一时刻参数标注形成一个格局,每一个格局中的红色标注个数称为格局的相关度;如果格局中所有的参数值都是红色标注则称为一个完全相关性格局;反之,如果格局中所有的参数值都为黑色标注则称为一个非相关性格局;通过格局对危险源参数相关性的刻画可以直观有效的了解乳化炸药生产线各个危险源之间变化的相互影响,进而可以考虑相关的处置措施;如图3所示,图中只是给出了危险源超出预测预警次数统计的按月统计的示意图。在该图中x轴的时间单位为天,y轴的单位为参数值预测预警次数。本模型中的预测预警统计分析可以按照不同的时间段进行统计分析,按月只是其中的一种情况。(3) Characterize the correlation of hazard source parameters: when a hazard source parameter exceeds the predicted warning value, the parameters are compounded together through the method of relative coordinate compounding, and the parameters exceeding the predicted warning value at the same time are marked in red. The parameters that do not exceed the predicted warning value are marked in black; the parameters marked at the same time form a pattern, and the number of red marks in each pattern is called the correlation degree of the pattern; if all the parameter values in the pattern are marked in red, it is called A complete correlation pattern; on the contrary, if all the parameter values in the pattern are marked in black, it is called a non-correlation pattern; by describing the correlation of hazard parameters in the pattern, it is possible to intuitively and effectively understand the relationship between each hazard of the emulsion explosive production line. Interaction between changes, and then relevant disposal measures can be considered; as shown in Figure 3, the figure only shows a monthly statistical diagram of the number of hazard sources exceeding the forecast and warning times. In this figure, the time unit of the x-axis is day, and the unit of the y-axis is the number of warnings predicted by the parameter value. The statistical analysis of forecast and early warning in this model can be carried out according to different time periods, and monthly is only one of them.

(4)生产线预测预警统计分析策略:采用粗糙集理论中的关联规则、概率统计中的期望与方差理论对每周、每月乃至更长时段的生产线上预测预警次数进行统计评估分析,并不给出具体每个危险源参数预测预警次数统计分析所用到的具体方法,这要根据实际应用场景来确定适用粗糙集理论中的关联规则或概率统计中的期望与方差理论;本模型只强调生产线预测预警次数的统计分析这种策略,适用与各个危险源参数。如图4所示,图中x轴为时间轴。y轴是一个复合轴,其取值单位是根据复合的参数取值的相对值,这样便于各种不同取值单位的参数可以在同一个坐标系下表示刻画。坐标系中除表示各个参数预警值界值8、正常生产中值7外,位于危险源参数上下预测预警界值内的点表示生产正常值6,位于相关危险源参数预测预警界值外的点表示预测预警值9。同一时间时刻表示各个参数的生产正常值6和预测预警值9共同组成一个格局,其中预测预警值9的个数称为格局的相关度。图中xj时刻格局为完全相关性格局,xm时刻格局为非相关性格局,xi时刻则为参数2、参数3相关的相关度为2的格局。图4给出了四个参数的例子,实际应用中可以是多于或少于四个参数的形式。(4) Statistical analysis strategy for production line prediction and early warning: use the association rules in rough set theory and the expectation and variance theory in probability statistics to conduct statistical evaluation and analysis on the production line prediction and early warning times on a weekly, monthly or even longer period, and do not Give the specific methods used in the statistical analysis of the number of predictions and early warnings for each hazard parameter, which should be determined according to the actual application scenario. The association rules in rough set theory or the expectation and variance theory in probability statistics are applicable; this model only emphasizes the production line The strategy of statistical analysis of predictive warning times is applicable to the parameters of each hazard source. As shown in Figure 4, the x-axis in the figure is the time axis. The y-axis is a composite axis, and its value unit is the relative value of the composite parameter value, so that parameters of various value units can be expressed and described in the same coordinate system. In the coordinate system, in addition to indicating the warning value boundary value of each parameter 8 and the normal production median value 7, the points located within the upper and lower prediction warning boundary values of the hazard source parameters represent the normal production value 6, and the points located outside the relevant hazard source parameter prediction warning boundary values Indicates the predicted warning value of 9. At the same time, the production normal value 6 and the forecast warning value 9 of each parameter together form a pattern, and the number of the forecast warning value 9 is called the correlation degree of the pattern. In the figure, the pattern at time x j is a complete correlation pattern, the pattern at time x m is a non-correlation pattern, and the pattern at time x i is a pattern with a correlation degree of 2 related to parameter 2 and parameter 3. Figure 4 shows an example of four parameters, which may be more or less than four parameters in practical applications.

实施例Example

本发明为乳化炸药生产工艺过程中危险源预测预警检测模型,该模型可以采用诸如计算机软件系统等方式来具体实施。这里只给出发明内容的实施步骤如下:The invention is a hazard source prediction, early warning and detection model in the production process of emulsion explosives, and the model can be specifically implemented by means such as a computer software system. The implementation steps that only provide the content of the invention are as follows:

第一步,设定乳化炸药生产工艺流程中的各个危险源及其参数。The first step is to set each hazard source and its parameters in the process flow of emulsion explosive production.

第二步,设定各个危险源参数的生产线自锁阈值、生产预期值以及预测预警上下界值。The second step is to set the production line self-locking threshold, production expected value, and forecast and warning upper and lower bounds of each hazard parameter.

第三步,实时检测各个危险源的参数信息。The third step is to detect the parameter information of each hazard source in real time.

第四步,当危险源参数超过预测预警值时,计算参数波动的变化率。The fourth step is to calculate the rate of change of parameter fluctuations when the hazard source parameters exceed the predicted warning value.

第五步,在第四步的同时,找出该时刻的危险源参数相关性格局并对超出预测预警的危险源进行相应的处置举措。The fifth step, at the same time as the fourth step, find out the correlation pattern of the hazard parameters at that moment and take corresponding measures to deal with the hazards beyond the forecast and warning.

第六步,对危险源参数预测预警次数进行统计分析,或返回第三步保持对各个危险源参数的实时检测。The sixth step is to perform statistical analysis on the number of hazard source parameter prediction and warning times, or return to the third step to maintain real-time detection of each hazard source parameter.

以上所举实施例为本发明的较佳实施方式,仅用来方便说明本发明,并非对本发明作任何形式上的限制,任何所属技术领域中具有通常知识者,若在不脱离本发明所提技术特征的范围内,利用本发明所揭示技术内容所作出局部更动或修饰的等效实施例,并且未脱离本发明的技术特征内容,均仍属于本发明技术特征的范围内。The above examples are preferred implementations of the present invention, and are only used to illustrate the present invention conveniently, and are not intended to limit the present invention in any form. Anyone with ordinary knowledge in the technical field, if they do not depart from the present invention, Within the scope of the technical features, the equivalent embodiments that utilize the technical content disclosed in the present invention to make partial changes or modifications without departing from the technical features of the present invention still belong to the scope of the technical features of the present invention.

Claims (4)

1. in an emulsion explosive production technology based on the prediction and warning detection model of dangerous matter sources, it is characterized in that, this model comprises following four parts: (1) sets up dangerous matter sources prediction and warning value: set up each dangerous matter sources prediction and warning value based on Emulsion Explosive Production process equipment parameter threshold; Described device parameter threshold value, refers to that whole production line deadlock, stopping are produced after production equipment reaches parameter threshold; Described dangerous matter sources prediction and warning value is less than corresponding device parameter threshold value; (2) dangerous matter sources Parameters variation fluctuation tolerance: when the parameter value of apparatus for production line reaches or exceeds hazard source prediction and warning value, utilize adjacent two time intervals determine the rate of change of the slope of straight line as dangerous matter sources parameter fluctuation value, the grade that the rate of change of dangerous matter sources parameter value is used as prediction and warning response mechanism according to and the foundation that detects of dangerous matter sources equipment latent instability factor; (3) dangerous matter sources dependence on parameter is portrayed: when certain dangerous matter sources parameter exceeds prediction and warning value, by the method for relative coordinate compound, parameters is combined with each other, synchronization exceeds the parameter of prediction and warning value all with red mark, the parameter not exceeding prediction and warning value then marks with black; Synchronization parameter mark formation general layout, the redness mark number in each general layout is called the degree of correlation of general layout; If parameter values all in general layout is all red mark, be called a complete correlativity general layout; Otherwise, if parameter values all in general layout is all black mark, be called a non-correlation general layout; Intuitively effectively can understand to portraying of dangerous matter sources dependence on parameter influencing each other of changing between each dangerous matter sources of emulsion explosive production line by general layout, and then the Disposal Measures of being correlated with can be considered; (4) production line prediction and warning statistical study strategy: adopt the correlation rule in rough set theory, expectation in probability statistics and deviation theory to carry out statistical estimation analysis to prediction and warning number of times on the production line of weekly, monthly and even more long duration; This strategy of statistical study of production line prediction and warning number of times only emphasized by this model, is suitable for and each dangerous matter sources parameter.
2. in emulsion explosive production technology according to claim 1 based on the prediction and warning detection model of dangerous matter sources, it is characterized in that, step (1) described dangerous matter sources prediction and warning value is the less fluctuation range of delimiting according to production equipment parameters value under normal production scenarios.
3. in emulsion explosive production technology according to claim 1 based on the prediction and warning detection model of dangerous matter sources, it is characterized in that, the described rate of change formula of step (2) is: k=(y 2-y 1)/(x 2-x 1); Wherein: when device parameter value is higher than the dangerous matter sources prediction and warning value upper bound, the rate of change of dangerous matter sources parameter fluctuation value is just, the rate of change of the slope larger explanation dangerous matter sources parameter fluctuation value of straight line is larger; When device parameter value is lower than dangerous matter sources prediction and warning value lower bound, the rate of change of dangerous matter sources parameter fluctuation value is negative value, and the rate of change of the slope less explanation dangerous matter sources parameter fluctuation value of straight line is larger.
4. in emulsion explosive production technology according to claim 1 based on the prediction and warning detection model of dangerous matter sources, it is characterized in that, described in step (4), statistical estimation analysis is carried out to prediction and warning number of times on the production line of weekly, monthly and even more long duration, do not provide the concrete grammar used by the statistical study of concrete each dangerous matter sources parameter prediction early warning number of times, this will determine to be suitable for the correlation rule in rough set theory or the expectation in probability statistics and deviation theory according to practical application scene.
CN201410735325.4A 2014-12-04 2014-12-04 Forecasting and early warning detection model in emulsion explosive production technological process based on danger source Expired - Fee Related CN104464232B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410735325.4A CN104464232B (en) 2014-12-04 2014-12-04 Forecasting and early warning detection model in emulsion explosive production technological process based on danger source

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410735325.4A CN104464232B (en) 2014-12-04 2014-12-04 Forecasting and early warning detection model in emulsion explosive production technological process based on danger source

Publications (2)

Publication Number Publication Date
CN104464232A true CN104464232A (en) 2015-03-25
CN104464232B CN104464232B (en) 2017-02-22

Family

ID=52910208

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410735325.4A Expired - Fee Related CN104464232B (en) 2014-12-04 2014-12-04 Forecasting and early warning detection model in emulsion explosive production technological process based on danger source

Country Status (1)

Country Link
CN (1) CN104464232B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113515891A (en) * 2021-06-04 2021-10-19 浙江永联民爆器材有限公司 Method for predicting and optimizing quality of emulsion explosive
CN117010690A (en) * 2023-08-04 2023-11-07 洛阳炼化宏达实业有限责任公司 Production safety early warning method based on artificial intelligence

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4938143A (en) * 1987-04-29 1990-07-03 Trojan Corporation Booster shaped for high-efficiency detonating
CN101333137A (en) * 2008-07-11 2008-12-31 华中科技大学 A safety monitoring method for continuous operation of an emulsifier
CN201654551U (en) * 2010-04-06 2010-11-24 陕西红旗民爆集团股份有限公司 An early warning monitoring and detection device for the safe operation of an emulsifier in an explosives production line
CN201737859U (en) * 2010-07-19 2011-02-09 广东华威化工实业有限公司 Emulsor safety monitoring interlock protector
CN102063119A (en) * 2010-11-11 2011-05-18 北京三博中自科技有限公司 Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data
WO2011086805A1 (en) * 2010-01-14 2011-07-21 株式会社日立製作所 Anomaly detection method and anomaly detection system
CN202465552U (en) * 2011-12-16 2012-10-03 煤炭科学研究总院爆破技术研究所 Continuous intelligent emulsifying machine for emulsified explosive

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4938143A (en) * 1987-04-29 1990-07-03 Trojan Corporation Booster shaped for high-efficiency detonating
CN101333137A (en) * 2008-07-11 2008-12-31 华中科技大学 A safety monitoring method for continuous operation of an emulsifier
WO2011086805A1 (en) * 2010-01-14 2011-07-21 株式会社日立製作所 Anomaly detection method and anomaly detection system
CN201654551U (en) * 2010-04-06 2010-11-24 陕西红旗民爆集团股份有限公司 An early warning monitoring and detection device for the safe operation of an emulsifier in an explosives production line
CN201737859U (en) * 2010-07-19 2011-02-09 广东华威化工实业有限公司 Emulsor safety monitoring interlock protector
CN102063119A (en) * 2010-11-11 2011-05-18 北京三博中自科技有限公司 Equipment failure prediction method based on point polling data and DCS (Data Communication System) online data
CN202465552U (en) * 2011-12-16 2012-10-03 煤炭科学研究总院爆破技术研究所 Continuous intelligent emulsifying machine for emulsified explosive

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113515891A (en) * 2021-06-04 2021-10-19 浙江永联民爆器材有限公司 Method for predicting and optimizing quality of emulsion explosive
CN113515891B (en) * 2021-06-04 2024-02-20 浙江永联民爆器材有限公司 Emulsion explosive quality prediction and optimization method
CN117010690A (en) * 2023-08-04 2023-11-07 洛阳炼化宏达实业有限责任公司 Production safety early warning method based on artificial intelligence
CN117010690B (en) * 2023-08-04 2024-11-05 洛阳炼化宏达实业有限责任公司 Production safety early warning method based on artificial intelligence

Also Published As

Publication number Publication date
CN104464232B (en) 2017-02-22

Similar Documents

Publication Publication Date Title
CN103984995B (en) The decision method of deep-foundation pit engineering risk warning indexes based on profit danger equalization point
CA2899201C (en) Method and system for intrusion and extrusion detection
WO2013090910A3 (en) Real-time anomaly detection of crowd behavior using multi-sensor information
CN103901298A (en) Method and system for detecting operating states of substation equipment
JP2012239085A5 (en)
CN104731914A (en) Method for detecting user abnormal behavior based on behavior similarity
CN104954192A (en) Network flow monitoring method and device
CN105205002B (en) A kind of software safety defect based on test job amount finds the modeling method of model
CN105825344A (en) Nuclear power object protection effectiveness quantifying and evaluating method and device
CN108922168A (en) A kind of mid-scale view Frequent Accidents road sentences method for distinguishing
CN202946195U (en) Image type intelligent detector for tunnel surrounding rock deformation
CN104464232B (en) Forecasting and early warning detection model in emulsion explosive production technological process based on danger source
CN108343843B (en) Oil and gas pipeline defect maintenance determination method and device
CN116467493A (en) Mine disaster tracing method based on knowledge graph
CN103912538A (en) Hydraulic oil level monitoring method and hydraulic oil level monitoring equipment
CN104200599B (en) Multi-sensor fire detection method for buses
CN105632114A (en) Monitoring measurement point safety state monitoring method based on GIS technology
CN1472674A (en) Dynamic Adaptive Alarm Method of Equipment State Based on Probabilistic Model
CN109688112A (en) Industrial Internet of Things unusual checking device
CN106354940A (en) Landscape water quality simulation and early warning method based on water quality model uncertainty input
CN103528844B (en) structural damage early warning method based on empirical mode decomposition
CN104036362A (en) Rapid detection method of transformer power load abnormal data
CN113009817B (en) Industrial control system intrusion detection method based on controller output state safety entropy
CN106442830B (en) The detection method and system of gas content in transformer oil warning value
TWI636276B (en) Method of determining earthquake with artificial intelligence and earthquake detecting system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: 514700 two building, 3-4 A1 building, 51 Meixian people's road, Meizhou, Guangdong.

Patentee after: GUANGDONG ZHENSHENG PACKAGING TECHNOLOGY Co.,Ltd.

Patentee after: ZHENGZHOU University OF LIGHT INDUSTRY

Patentee after: Guangdong four o one factory Co.,Ltd.

Address before: 514700 two building, 3-4 A1 building, 51 Meixian people's road, Meizhou, Guangdong.

Patentee before: GUANGDONG ZHENSHENG PACKAGING TECHNOLOGY Co.,Ltd.

Patentee before: ZHENGZHOU University OF LIGHT INDUSTRY

Patentee before: GUANGDONG NO.401 FACTORY

CP01 Change in the name or title of a patent holder
CP01 Change in the name or title of a patent holder

Address after: 514700 two building, 3-4 A1 building, 51 Meixian people's road, Meizhou, Guangdong.

Patentee after: Guangdong Zhensheng Technology Group Co.,Ltd.

Patentee after: ZHENGZHOU University OF LIGHT INDUSTRY

Patentee after: Guangdong four o one factory Co.,Ltd.

Address before: 514700 two building, 3-4 A1 building, 51 Meixian people's road, Meizhou, Guangdong.

Patentee before: GUANGDONG ZHENSHENG PACKAGING TECHNOLOGY Co.,Ltd.

Patentee before: ZHENGZHOU University OF LIGHT INDUSTRY

Patentee before: Guangdong four o one factory Co.,Ltd.

CP01 Change in the name or title of a patent holder
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20170222

CF01 Termination of patent right due to non-payment of annual fee