Coal rock dynamic disaster while-drilling multi-element signal sensing and early warning method

Abstract

A while-drilling multi-element signal sensing and early warning method for coal rock dynamic disasters comprises the steps that in the early stage of coal seam recovery, bedding gas extraction drilling is utilized, while-drilling signals generated in the drilling period of each drill rod are collected in real time through a multi-parameter sensing system integrated with a drilling machine, and while-drilling data are obtained based on the while-drilling signals; constructing a mechanical parameter inversion model, and calculating the compressive strength of the coal rock mass; a gas parameter inversion model is constructed, and gas pressure and coal rock mass permeability are obtained through decoupling; according to the method, coal rock mass compressive strength, gas pressure and coal rock mass permeability are used as core indexes, a spatial interpolation method is adopted to realize continuous representation of disaster risk distribution of a whole area, and a comprehensive risk index is established accordingly; and according to the value range of the comprehensive risk index, further quantifying the risk level of the coal and rock mass dynamic disaster based on the comprehensive risk index. According to the method, real-time sensing, accurate inversion and active prevention and control of coal rock dynamic disasters can be realized, and the problems of low detection accuracy, poor real-time performance, insufficient overall performance and the like in the traditional technology can be effectively solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent coal mine safety monitoring, and specifically is a method for sensing and warning of coal and rock dynamic disasters while drilling using multiple signals. Background Art

[0002] Coal and rock dynamic hazards are a key factor restricting safe coal mine production. Their occurrence is closely related to the stress distribution of coal seams, the presence of gas, and the mechanical properties of coal and rock masses. With increasing mining depths, coal and rock dynamic hazards are exhibiting new characteristics: increased concealment, wider impacts, and high destructive energy levels. These hazards pose a serious threat to the safety of underground workers and the operational safety of equipment and facilities. Therefore, efficient and accurate identification and early warning of coal and rock dynamic hazards have become a critical technical challenge that urgently needs to be addressed in the field of coal mine safety technology.

[0003] At present, the prevention and control of coal mine disasters mainly rely on geophysical prospecting and drilling technology, but both have obvious technical bottlenecks in practical application. Geophysical prospecting methods are severely limited by insufficient excitation source energy and severe interference from the complex underground environment, and have a series of problems such as high multi-solution and low detection accuracy. Traditional drilling technology directly obtains coal and rock parameters through borehole sampling, ground stress testing, etc., which has the advantages of high measurement accuracy and reliable detection information, but its core problem lies in "one-hole view" - single-hole data can only reflect local coal and rock characteristics, and cannot globally characterize the spatial distribution of coal seam stress, permeability and gas pressure. If full coverage is to be achieved, a large number of dense boreholes are often required, resulting in a significant increase in engineering volume and cost, which limits the promotion and application of this method in actual production.

[0004] At the same time, a large number of in-beam boreholes are drilled during coal mining. These boreholes serve as the basic engineering units for regional gas control, but the vast amount of potential information generated during the drilling process is not effectively utilized. Dynamic signals generated during the drilling process, such as torque fluctuations, mechanical strength of coal and rock masses, and gas outburst volume, contain coupled response relationships between multiple physical fields such as coal structure, stress perturbations, and gas seepage. However, traditional drilling methods, which focus on end-hole sampling and static testing, fail to fully tap into this real-time dynamic information. As a result, key parameters such as coal and rock stress distribution and gas occurrence status remain "unidentified and difficult to perceive" for a long time, seriously restricting the early identification and precise prevention and control of coal and rock dynamic hazards.

[0005] In addition, there are still key technical difficulties in the existing gas parameter inversion research. Coalbed gas will be affected by both gas pressure and permeability during its migration, and the two are coupled with each other in the seepage equation. Relying solely on a single known quantity (i.e., the gas flow rate at the borehole mouth) to invert two unknown parameters has problems such as multiple solutions and uncertainty, resulting in poor accuracy of the inversion results and insufficient physical credibility. At the same time, the permeability of the coal body is affected by stress disturbances and fracture connectivity, and often presents nonlinear and inhomogeneous spatial variation patterns, making the inversion calculation more difficult. Existing methods mostly rely on empirical parameter adjustment or least squares fitting, lack physical constraints on parameter continuity, and are difficult to effectively solve the multiple solution problem in the inversion process.

[0006] In response to the above technical bottlenecks, there is an urgent need to provide a detection and early warning method that can integrate dynamic signals while drilling, decouple multiple parameters, and break through the limitations of single-hole data, so as to achieve real-time perception, accurate inversion and active prevention and control of coal and rock dynamic disasters. Summary of the Invention

[0007] In response to the problems existing in the above-mentioned existing technologies, the present invention provides a method for multi-signal perception and early warning of coal and rock dynamic disasters while drilling. The method has a simple implementation process and low implementation cost. It can realize real-time perception, precise inversion and active prevention and control of coal and rock dynamic disasters, and can effectively solve the core problems of traditional technologies such as low detection accuracy, poor real-time performance, and insufficient globality.

[0008] To achieve the above objectives, the present invention provides a method for sensing and warning coal and rock dynamic disasters while drilling using multiple signals, comprising the following steps:

[0009] Step 1: Drilling parameter collection;

[0010] In the early stage of coal seam recovery, the drilling rig integrates a multi-parameter sensor system to collect the drilling signals generated by each drill rod during drilling in real time, and obtain drilling data based on the drilling signals.

[0011] Step 2: Construct a multivariate parameter inversion model;

[0012] S21: Construct a mechanical parameter inversion model; calculate the compressive strength σ of coal and rock mass based on drilling parameters c , as shown in formula (1);

[0013]

[0014] Where D is the drill bit diameter, a, b, and k are different constant parameters related to the mechanical properties of coal and rock mass;

[0015] S22: Constructing gas parameter inversion model;

[0016] S22-1: First, based on Darcy's law, a partial differential equation for borehole gas flow is constructed, as shown in formula (2); then, a differential equation is constructed based on the partial differential equation for borehole gas flow, as shown in formula (3); then, the predicted value of the borehole gas outflow is solved by the iterative method.

[0017]

[0018] Where P is the gas pressure, r is the radial distance, t is the time, λ is the base permeability of the coal rock mass, is the porosity of coal rock mass, c, d, ρ, and B are constant parameters related to the flow and adsorption characteristics of coalbed methane;

[0019]

[0020] S22-2: Construct the objective function E(λ,P based on the error term and regularization term 0 ), as shown in formula (4);

[0021]

[0022] Where q obs is the measured value of gas outflow, q model is the predicted value of gas emission, α is the regularization weight coefficient;

[0023] S22-3: Optimization iterative algorithm; using the composite method as the global optimization strategy, the coal rock permeability and gas pressure are optimized synchronously in the continuous space, and the objective function E(λ,P 0 ) converges, completing the coupled inversion process of gas pressure and coal-rock permeability, and obtaining the spatial distribution information of gas pressure P and coal-rock permeability λ inside the coal seam;

[0024] Step 3: Highlight comprehensive early warning of hazards;

[0025] S31: Index extraction; segment the drilling data of each borehole along the drilling direction, and use the gas pressure P i , coal rock permeability λ i and coal rock mass compressive strength σ c The three are core parameters, and they are standardized and mapped to the [0,1] interval to form a three-dimensional dynamic quantitative index for identifying coal and rock dynamic disasters, as shown in formula (5);

[0026]

[0027] S32: Regional risk construction; use spatial interpolation method to calculate the gas pressure P of each borehole i , coal rock permeability λi and coal rock mass compressive strength σ c The three types of gradient indicators are spatially fitted to construct a continuous and smooth regional function surface, achieving a continuous representation of the disaster risk distribution in the entire construction area;

[0028] S33: Build a comprehensive risk early warning system;

[0029] S33-1: Based on the historical gas outburst accident cases in the current mining area, a data-driven method is used to determine the relative weights of three key disaster-causing factors: the energy state of gas storage, the degree of stress concentration, and the mechanical strength of coal and rock mass. According to formula (6), a comprehensive risk index I is constructed. i , which is used to quantify the risk level of coal rock mass dynamic disasters;

[0030]

[0031] Where w1, w2, and w3 are weighted coefficients of the energy state of gas occurrence, stress concentration, and mechanical strength index of coal and rock mass, respectively, and satisfy w1+w2+w3=1;

[0032] S33-2: Based on the comprehensive risk index I i The value range of the dynamic disaster risk level is divided into five levels; when 0.00≤I i <0.20, the current area is judged as a risk-free area; when 0.20≤I i <0.40, the current area is judged to be a low-risk area; when 0.40≤I i <0.60, the current area is judged to be a medium-risk area; when 0.60≤I i <0.80, the current area is judged as a high-risk area; when 0.80≤I i When ≤1.00, the current area is judged to be an extremely high-risk area;

[0033] S33-3: By combining drilling paths with construction sequence information, advanced dynamic early warning is carried out for high-risk areas and areas above high-risk areas to achieve active and precise prevention and control of coal-rock dynamic disasters.

[0034] Furthermore, in order to subsequently obtain accurate gas pressure, coal rock permeability and coal rock compressive strength data, in step 1, the drilling signal includes drill bit torque M, feed force F, drilling speed V, rotation speed N, and orifice gas outflow rate q.

[0035] As a preferred embodiment, in step one, the drilling signal is uploaded to the ground monitoring platform in real time through the downhole data acquisition and transmission system, and during the transmission process, the synchronization of the signal timing and the integrity of the data are ensured.

[0036] As a preference, in step three S32, the spatial interpolation method includes Kriging interpolation, cubic spline interpolation and inverse distance weighted interpolation.

[0037] As a preference, in step three S33-1, the data-driven method includes neural network, grey relational analysis and fuzzy logic reasoning.

[0038] The present invention discloses a method for sensing and warning of coal-rock dynamic disasters while drilling using multiple signals. During the gas control drilling process, the method uses a sensor system integrated with the drilling rig to dynamically collect multiple signals while drilling in real time. The method first combines the coal-rock mechanical parameter inversion model to obtain the coal-rock compressive strength, which can characterize the mechanical strength of the coal-rock mass. The method then combines the gas migration inversion model to decouple the gas pressure from the coal-rock permeability. The decoupled gas pressure directly reflects the energy state of gas storage, while the coal-rock permeability effectively reflects the degree of stress concentration. The obtained coal-rock compressive strength, gas pressure, and coal-rock permeability are then used as core indicators. A spatial interpolation method is then used to achieve a continuous characterization of the disaster risk distribution across the entire region. Based on this, a comprehensive risk index is established, and the risk level of coal-rock dynamic disasters is further quantified based on the comprehensive risk index. This approach has led to the construction of a dynamic early warning system based on the multi-field coupling of "gas energy, stress concentration, and mechanical strength," achieving a shift from point-based monitoring to surface-based monitoring, and from intermittent to continuous monitoring, thereby improving the accuracy and efficiency of coal and rock dynamic disaster monitoring and early warning. Using this method, during pre-mining gas control drilling operations, sensors integrated into the drill rig can be used to simultaneously collect drilling mechanical parameters and gas flow data. This allows a single borehole to perform both control and detection functions, eliminating the need for additional dedicated detection holes, avoiding large-scale detection operations, and significantly reducing workload.

[0039] This method has a simple implementation process and low implementation cost. Through the dynamic collection and coupling analysis of multi-element signals while drilling, combined with the coal rock mechanics-gas migration inversion model, a dangerous area early warning system with multi-porous data fusion is constructed, which realizes the dynamic identification of coal rock dynamic disasters and regional risk classification assessment, and can realize real-time perception, accurate inversion and active prevention and control of coal rock dynamic disasters, thus solving the core problems of low detection accuracy, poor real-time performance and insufficient globality in traditional technologies. It is suitable for dynamic disaster monitoring and early warning in coal mining process. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 is a flow chart of the present invention;

[0041] Figure 2 A schematic diagram of a drilling operation using a drilling rig with an integrated multi-parameter sensing system during regional gas control in the present invention;

[0042] Figure 3This is a schematic diagram of the iterative process when the composite method is used to solve the objective function in the present invention.

[0043] In the figure: 1. Drill hole, 2. Drill rod, 3. Auger rod, 4. Rock drill, 5. Fixed column, 6. Slide, 7. Gas flow meter, 8. Sampler, 9. Valve. DETAILED DESCRIPTION

[0044] The present invention will be further described below with reference to the accompanying drawings.

[0045] like Figure 1 and Figure 2 As shown, the present invention provides a method for sensing and warning coal and rock dynamic disasters while drilling with multiple signals, including the following steps:

[0046] Step 1: Drilling parameter collection;

[0047] In the early stage of coal seam recovery, the drilling rig integrates a multi-parameter sensor system to collect the drilling signals generated by each drill rod during drilling in real time, and obtain drilling data based on the drilling signals.

[0048] exist Figure 2 , a schematic diagram showing a state of drilling in a borehole 1 driven by a rock drill 4 driving a drill rod 2 and an auger rod 3 is shown. The rock drill 4 is mounted on a carriage 6, which is supported by a fixed column 5. An air flow meter 7 is connected to the borehole 1 for collecting the gas outflow rate q at the orifice. A sampler 8 is connected to the borehole 1 and is equipped with a valve 9 for sampling.

[0049] Step 2: Construct a multivariate parameter inversion model;

[0050] S21: Construct a mechanical parameter inversion model; calculate the compressive strength σ of coal and rock mass based on drilling parameters c , which is used to reflect the mechanical strength of coal rock mass, as shown in formula (1);

[0051]

[0052] Where D is the drill bit diameter, a, b, and k are different constant parameters related to the mechanical properties of coal and rock mass;

[0053] S22: Constructing gas parameter inversion model;

[0054] S22-1: First, based on Darcy's law, a partial differential equation for borehole gas flow is constructed, as shown in formula (2); then, a differential equation is constructed based on the partial differential equation for borehole gas flow, as shown in formula (3); then, the predicted value of the borehole gas outflow is solved by the iterative method.

[0055]

[0056] Where P is the gas pressure, r is the radial distance, t is the time, λ is the base permeability of the coal rock mass, is the porosity of coal rock mass, c, d, ρ, and B are constant parameters related to the flow and adsorption characteristics of coalbed methane;

[0057]

[0058] S22-2: Construct the objective function E(λ,P based on the error term and regularization term 0 ), as shown in formula (4); where the error term is the residual sum of squares between the forward solution model prediction value and the measured orifice gas flow rate, and the regularization term is the L-term of the spatial continuity of gas permeability and initial pressure. 2 Regularization constraints;

[0059]

[0060] Where q obs is the measured value of gas outflow, q model is the predicted value of gas emission, α is the regularization weight coefficient;

[0061] S22-3: Optimization iterative algorithm; using the composite method as the global optimization strategy, the coal rock permeability and gas pressure are optimized synchronously in the continuous space, and the objective function E(λ,P 0 ) converges, completing the coupled inversion process of gas pressure and coal-rock permeability, and obtaining the spatial distribution information of gas pressure P inside the coal seam and coal-rock permeability λ, as shown in Figure 3 As shown;

[0062] Among them, the gas pressure P can directly reflect the energy state of coal seam gas storage. The larger P is, the greater the gas accumulation energy is and the higher the risk of dynamic disasters is. The coal rock permeability λ reflects the seepage capacity of coal rock fractures. The higher the stress concentration degree and the worse the fracture connectivity, the smaller the λ value is.

[0063] Step 3: Highlight comprehensive early warning of hazards;

[0064] S31: Index extraction; segment the drilling data of each borehole along the drilling direction, and use the gas pressure P i , coal rock permeability λ i and coal rock mass compressive strength σ c The three are core parameters, and they are standardized and mapped to the [0,1] interval to form a three-dimensional dynamic quantitative index for identifying coal and rock dynamic disasters, as shown in formula (5);

[0065]

[0066] S32: Regional risk construction; use spatial interpolation method to calculate the gas pressure P of each borehole i , coal rock permeability λ i and coal rock mass compressive strength σ c The three types of gradient indicators are spatially fitted to construct a continuous and smooth regional function surface, achieving a continuous representation of the disaster risk distribution in the entire construction area;

[0067] S33: Construction of comprehensive risk early warning system;

[0068] S33-1: Based on the historical gas outburst accident cases in the current mining area, a data-driven method is used to determine the relative weights of three key disaster-causing factors: the energy state of gas storage, the degree of stress concentration, and the mechanical strength of coal and rock mass. According to formula (6), a comprehensive risk index I is constructed. i , which is used to quantify the risk level of coal rock mass dynamic disasters;

[0069]

[0070] Where w1, w2, and w3 are weighted coefficients of the energy state of gas occurrence, stress concentration, and mechanical strength index of coal and rock mass, respectively, and satisfy w1+w2+w3=1;

[0071] S33-2: Based on the comprehensive risk index I i The value range of the dynamic disaster risk level is divided into five levels; when 0.00≤I i <0.20, the current area is judged as a risk-free area; when 0.20≤I i <0.40, the current area is judged to be a low-risk area; when 0.40≤I i <0.60, the current area is judged to be a medium-risk area; when 0.60≤I i <0.80, the current area is judged as a high-risk area; when 0.80≤I i When ≤1.00, the current area is judged to be an extremely high-risk area (potential danger point for major power disasters);

[0072] S33-3: By combining drilling paths with construction sequence information, advanced dynamic early warning is carried out for high-risk areas and areas above high-risk areas to achieve active and precise prevention and control of coal-rock dynamic disasters.

[0073] In order to subsequently obtain accurate gas pressure, coal rock permeability and coal rock compressive strength data, in step 1, the drilling signals include drill bit torque M, feed force F, drilling speed V, rotation speed N, and orifice gas outflow rate q.

[0074] As a preferred embodiment, in step one, the drilling signal is uploaded to the ground monitoring platform in real time through the downhole data acquisition and transmission system, and during the transmission process, the synchronization of the signal timing and the integrity of the data are ensured.

[0075] As a preference, in step three S32, the spatial interpolation method includes Kriging interpolation, cubic spline interpolation, inverse distance weighted interpolation, etc.

[0076] As a preference, in step three S33-1, the data-driven method includes neural network, grey relational analysis and fuzzy logic reasoning, etc.

[0077] The present invention discloses a method for sensing and warning of coal-rock dynamic disasters while drilling using multiple signals. During the gas control drilling process, the method uses a sensor system integrated with the drilling rig to dynamically collect multiple signals while drilling in real time. The method first combines the coal-rock mechanical parameter inversion model to obtain the coal-rock compressive strength, which can characterize the mechanical strength of the coal-rock mass. The method then combines the gas migration inversion model to decouple the gas pressure from the coal-rock permeability. The decoupled gas pressure directly reflects the energy state of gas storage, while the coal-rock permeability effectively reflects the degree of stress concentration. The obtained coal-rock compressive strength, gas pressure, and coal-rock permeability are then used as core indicators. A spatial interpolation method is then used to achieve a continuous characterization of the disaster risk distribution across the entire region. Based on this, a comprehensive risk index is established, and the risk level of coal-rock dynamic disasters is further quantified based on the comprehensive risk index. This approach has led to the construction of a dynamic early warning system based on the multi-field coupling of "gas energy, stress concentration, and mechanical strength," achieving a shift from point-based monitoring to surface-based monitoring, and from intermittent to continuous monitoring, thereby improving the accuracy and efficiency of coal and rock dynamic disaster monitoring and early warning. Using this method, during pre-mining gas control drilling operations, sensors integrated into the drill rig can be used to simultaneously collect drilling mechanical parameters and gas flow data. This allows a single borehole to perform both control and detection functions, eliminating the need for additional dedicated detection holes, avoiding large-scale detection operations, and significantly reducing workload.

[0078] This method has a simple implementation process and low implementation cost. Through the dynamic collection and coupling analysis of multi-element signals while drilling, combined with the coal rock mechanics-gas migration inversion model, a dangerous area early warning system with multi-porous data fusion is constructed, which realizes the dynamic identification of coal rock dynamic disasters and regional risk classification assessment, and can realize real-time perception, accurate inversion and active prevention and control of coal rock dynamic disasters, thereby solving the core problems of low detection accuracy, poor real-time performance and insufficient globality in traditional technologies. It is suitable for dynamic disaster monitoring and early warning in coal mining processes.

Claims

1. A method for sensing and warning coal and rock dynamic disasters while drilling with multiple signals, characterized in that: The following steps are involved: Step 1: Drilling parameter collection; In the early stage of coal seam recovery, the drilling rig integrates a multi-parameter sensor system to collect the drilling signals generated by each drill rod during drilling in real time, and obtain drilling data based on the drilling signals. Step 2: Construct a multivariate parameter inversion model; S21: Construct a mechanical parameter inversion model; calculate the compressive strength σ of coal and rock mass based on drilling parameters c , as shown in formula (1); Where D is the drill bit diameter, a, b, and k are different constant parameters related to the mechanical properties of coal and rock mass; S22: Constructing gas parameter inversion model; S22-1: First, based on Darcy's law, a partial differential equation for borehole gas flow is constructed, as shown in formula (2); then, a differential equation is constructed based on the partial differential equation for borehole gas flow, as shown in formula (3); then, the predicted value of the borehole gas outflow is solved by the iterative method. Where P is the gas pressure, r is the radial distance, t is the time, λ is the base permeability of the coal rock mass, is the porosity of coal rock mass, c, d, ρ, and B are constant parameters related to the flow and adsorption characteristics of coalbed methane; S22-2: Construct the objective function E(λ,P based on the error term and regularization term 0 ), as shown in formula (4); Where q obs is the measured value of gas outflow, q model is the predicted value of gas emission, α is the regularization weight coefficient; S22-3: Optimization iterative algorithm; using the composite method as the global optimization strategy, the coal rock permeability and gas pressure are optimized synchronously in the continuous space, and the objective function E(λ,P 0 ) converges, completing the coupled inversion process of gas pressure and coal-rock permeability, and obtaining the spatial distribution information of gas pressure P and coal-rock permeability λ inside the coal seam; Step 3: Highlight comprehensive early warning of hazards; S31: indicator extraction; The drilling data of each borehole are processed in sections along the drilling direction, and the gas pressure P i , coal rock permeability λ i and coal rock mass compressive strength σ c The three are core parameters, and they are standardized and mapped to the [0,1] interval to form a three-dimensional dynamic quantitative index for identifying coal and rock dynamic disasters, as shown in formula (5); S32: Regional risk construction; use spatial interpolation method to calculate the gas pressure P of each borehole i , coal rock permeability λ i and coal rock mass compressive strength σ c The three types of gradient indicators are spatially fitted to construct a continuous and smooth regional function surface, achieving a continuous representation of the disaster risk distribution in the entire construction area; S33: Build a comprehensive risk early warning system; S33-1: Based on the historical gas outburst accident cases in the current mining area, a data-driven method is used to determine the relative weights of three key disaster-causing factors: the energy state of gas storage, the degree of stress concentration, and the mechanical strength of coal and rock mass. According to formula (6), a comprehensive risk index I is constructed. i , which is used to quantify the risk level of coal rock mass dynamic disasters; Where w1, w2, and w3 are weighted coefficients of the energy state of gas occurrence, stress concentration, and mechanical strength index of coal and rock mass, respectively, and satisfy w1+w2+w3=1; S33-2: Based on the comprehensive risk index I i The value range of the dynamic disaster risk level is divided into five levels; when 0.00≤I i <0.20, the current area is judged as a risk-free area; When 0.20≤I i When <0.40, the current area is judged as a low-risk area; When 0.40≤I i When <0.60, the current area is judged as a medium-risk area; When 0.60≤I i When <0.80, the current area is judged as a high-risk area; When 0.80≤I i When ≤1.00, the current area is judged to be an extremely high-risk area; S33-3: By combining drilling paths with construction sequence information, advanced dynamic early warning is carried out for high-risk areas and areas above high-risk areas to achieve active and precise prevention and control of coal-rock dynamic disasters.

2. The method for sensing and warning of coal and rock dynamic disasters while drilling with multiple signals according to claim 1, characterized in that: In step 1, the drilling signals include drill bit torque M, feed force F, drilling speed V, rotation speed N, and orifice gas outflow q.

3. A method for sensing and warning coal and rock dynamic disasters while drilling with multiple signals according to claim 1 or 2, characterized in that: In step one, the downhole data acquisition and transmission system is used to upload the drilling signal to the ground monitoring platform in real time. During the transmission process, the synchronization of the signal timing and the integrity of the data are ensured.

4. The method for sensing and warning coal and rock dynamic disasters while drilling with multiple signals according to claim 1, characterized in that: In step 3 S32, the spatial interpolation method includes Kriging interpolation, cubic spline interpolation and inverse distance weighted interpolation.

5. The method for sensing and warning coal and rock dynamic disasters while drilling with multiple signals according to claim 1, characterized in that: In step three S33-1, the data-driven method includes neural network, grey relational analysis and fuzzy logic reasoning.

Images