A method for deploying safety monitoring sensors without blind spots

Abstract

The present invention provides a method for deploying safety monitoring sensors without blind spots, including: using an adaptive denoising function to remove abnormal values ​​in the measurement values ​​of each neighboring sensor to generate a measurement value after data cleaning; obtaining the trust of each neighboring sensor according to the measurement value after data cleaning; obtaining a fusion matrix between each sensor according to the trust of each neighboring sensor; using the fusion matrix to fuse the measurement values ​​collected by each neighboring sensor to obtain a fused measurement value; and deploying the sensor with the best position at a preset safety monitoring point according to the fused measurement value. The present invention finds the optimal monitoring position of a safety monitoring point by using the measurement values ​​after fusion of multiple sensors, and uses a new sensor to replace multiple sensors to collect environmental parameters of the safety monitoring point, which can ensure full coverage of the sensor network and solve the problem of cost increase and resource waste caused by too many sensors.

Description

Technical Field

[0001] The present invention belongs to the technical field of sensor deployment, and more specifically, relates to a method for deploying safety monitoring sensors without blind spots. Background Art

[0002] In modern construction processes, various sensors are used to monitor various safety parameters (such as the concentration of toxic gases, the concentration of combustible gases, etc.) to ensure the safety of construction workers.

[0003] At present, the layout of safety monitoring sensors generally relies on experience and lacks a theoretical basis. If the sensors are too sparsely laid out, the full coverage of the sensor network cannot be achieved, which can easily lead to various safety accidents; on the contrary, if the sensors are too densely distributed, the sensor areas in the sensor coverage range will overlap too much, resulting in increased costs and waste of resources. Therefore, in the sensor layout, it is necessary not only to meet the various performance constraints of the sensor, such as system energy loss, coverage accuracy, signal completeness, etc., but also to consider the cost of sensor deployment. Summary of the invention

[0004] In order to solve the above problems, an object of the present invention is to provide a method for deploying safety monitoring sensors without blind spots, so as to solve the problem of high deployment cost of safety monitoring sensors.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] A method for deploying safety monitoring sensors without blind spots, comprising:

[0007] Step 1: Place multiple neighboring sensors at preset safety monitoring points;

[0008] Step 2: Construct a measurement space model based on the distances between each neighboring sensor;

[0009] Step 3: Construct an adaptive denoising function based on the measurement space model;

[0010] Step 4: using the adaptive denoising function to remove abnormal values ​​in the measurement values ​​of each neighboring sensor to generate measurement values ​​after data cleaning;

[0011] Step 5: Obtain the trustworthiness of each neighboring sensor according to the measurement value after data cleaning;

[0012] Step 6: Obtain a trust matrix between each sensor according to the trust of each neighboring sensor;

[0013] Step 7: Obtain a fusion matrix according to the trust matrix between the sensors;

[0014] Step 8: Using the fusion matrix to fuse the measurement values ​​collected by each neighboring sensor to obtain a fused measurement value;

[0015] Step 9: Deploy the optimally positioned sensors at the preset safety monitoring points based on the fused measurement values.

[0016] Preferably, the step 2: constructing a measurement space model according to the distances between each neighboring sensor includes:

[0017] Using the formula:

[0018]

[0019] Construct a measurement space model; where σ represents the average value of the difference in measurement values ​​between the sensor at point m and the sensor at point n within a preset time period, dis(m,n) represents the distance between the sensor at point m and the sensor at point n, and R represents an adjustable parameter.

[0020] Preferably, the step 3: constructing an adaptive denoising function according to the measurement space model comprises:

[0021] Step 3.1: Construct a denoising threshold according to the weighted average of the measured values; wherein the denoising threshold is:

[0022]

[0023] Among them, Y i represents the i-th measurement value collected by the sensor, W i Represents Y i The weight value of

[0024] Step 3.2: construct an adaptive denoising function according to the adaptive denoising threshold and the measurement space model.

[0025] Preferably, the adaptive denoising function is:

[0026]

[0027] Among them, x(m,t) represents the measurement value of the sensor at point m at time t, x(n,t) represents the measurement value of the sensor at point n at time t, ρ represents the equilibrium threshold, |N m | represents the number of neighboring sensors,

[0028] Preferably, the step 6: obtaining a trust matrix between each sensor according to the trust of each neighboring sensor includes:

[0029] Using the formula:

[0030]

[0031] Construct a trust matrix; where d m,n (m,n=1,2,…k) represents the trust between the sensor at point m and the sensor at point n, d m,n =|Q m -Q n |, Q m represents the variance of the data collected by the sensor at point m, Q n Represents the variance of the data collected by the sensors at point n.

[0032] Preferably, the step 7: obtaining a fusion matrix according to the trust matrix between the sensors includes:

[0033] Step 7.1: Get the limit value;

[0034] Step 7.2: Construct a fusion matrix according to the limit value and the trust matrix; wherein the fusion matrix is:

[0035]

[0036]

[0037] Among them, α ij Indicates the limit value.

[0038] Preferably, the step 8: using the fusion matrix to fuse the measurement values ​​collected by each neighboring sensor to obtain a fused measurement value includes:

[0039] Step 8.1: Take the column or row with the most 1 values ​​in the fusion matrix as the preferred set;

[0040] Step 8.2: taking the measured values ​​of the sensors corresponding to the values ​​of 1 in the preferred set as the fusion set;

[0041] Step 8.3: Obtain a fused measurement value according to the fusion set; wherein the calculation formula of the fused measurement value is:

[0042]

[0043] Among them, T i is the i-th measurement value in the fusion set, and L is the number of elements in the fusion set.

[0044] Preferably, the step 9: deploying the optimally positioned sensor at the preset safety monitoring point according to the fused measurement values ​​includes:

[0045] Step 9.1: Randomly deploy new sensors around the preset safety monitoring points;

[0046] Step 9.2: Determine whether the absolute value of the difference between the new sensor's measurement value and the fused measurement value is greater than a preset threshold;

[0047] Step 9.3: If it is greater than the preset threshold, return to step 9.1;

[0048] Step 9.4: If it is less than the preset threshold, the current position of the new sensor is used as the optimal placement position of the sensor.

[0049] Preferably, the limit value ranges from [0.5-0.75].

[0050] The beneficial effect of the blind-zone-free deployment method of a safety monitoring sensor provided by the present invention is that: compared with the prior art, the deployment method of the present invention includes: using the adaptive denoising function to remove abnormal values ​​in the measurement values ​​of each neighboring sensor to generate a measurement value after data cleaning; obtaining the trust of each neighboring sensor according to the measurement value after data cleaning; obtaining the fusion matrix between each sensor according to the trust of each neighboring sensor; using the fusion matrix to fuse the measurement values ​​collected by each neighboring sensor to obtain the fused measurement value; and deploying the sensor with the best position at the preset safety monitoring point according to the fused measurement value. The present invention finds the optimal monitoring position of the safety monitoring point by using the measurement values ​​fused by multiple sensors, and uses a new sensor to replace multiple sensors to collect the environmental parameters of the safety monitoring point, which can ensure full coverage of the sensor network and solve the problem of cost increase and resource waste caused by too many sensors. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be 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.

[0052] Figure 1 A flow chart of a method for deploying safety monitoring sensors without blind spots provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0054] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0055] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0056] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] The purpose of the present invention is to provide a method for deploying safety monitoring sensors without blind spots, which can reduce the deployment cost of the safety monitoring sensors.

[0058] See also Figure 1 To achieve the above purpose, the technical solution adopted by the present invention is: a method for deploying safety monitoring sensors without blind spots, comprising:

[0059] Step 1: Place multiple neighboring sensors at preset safety monitoring points;

[0060] It should be noted that the models of the neighboring sensors in the present invention may be the same or different.

[0061] Step 2: Construct a measurement space model based on the distances between each neighboring sensor;

[0062] Furthermore, the step 2 comprises:

[0063] Using the formula:

[0064]

[0065] Construct a measurement space model; where σ represents the average value of the difference in measurement values ​​between the sensor at point m and the sensor at point n within a preset time period, dis(m,n) represents the distance between the sensor at point m and the sensor at point n, and R represents an adjustable parameter.

[0066] In the present invention, the sensors at point m and point n are neighboring sensors. The closer the positions of the two sensors are, the greater the correlation between the two sensors. Therefore, the present invention measures the correlation according to the Euclidean distance between the two sensors. In practical applications, since the sensor may be affected by its own parameters or environmental factors, the measured value collected by the sensor at a certain moment may deviate greatly from the actual value. Therefore, the present invention introduces an adjustable parameter R to correct the problem of deviation in sensor correlation caused by the influence of the sensor's own parameters or environmental factors.

[0067] Step 3: Construct an adaptive denoising function based on the measurement space model;

[0068] Furthermore, the step 3 comprises:

[0069] Step 3.1: Construct a denoising threshold according to the weighted average of the measured values; wherein the denoising threshold is:

[0070]

[0071] Among them, Y i represents the i-th measurement value collected by the sensor, W i Represents Y i It should be noted that, in the present invention, the weight value of each sensor can be set with reference to the model of each sensor. i If the models of all sensors are the same, W i Set to 1.

[0072] Step 3.2: Construct an adaptive denoising function according to the adaptive denoising threshold and the measurement space model. The adaptive denoising function is:

[0073]

[0074] Among them, x(m,t) represents the measurement value of the sensor at point m at time t, x(n,t) represents the measurement value of the sensor at point n at time t, ρ represents the equilibrium threshold, |N m| represents the number of neighboring sensors,

[0075] Step 4: using the adaptive denoising function to remove abnormal values ​​in the measurement values ​​of each neighboring sensor to generate measurement values ​​after data cleaning;

[0076] The present invention provides an adaptive denoising function to remove abnormal values, which can eliminate the problem that the measured value collected by the sensor at a certain moment deviates greatly from the actual value due to the influence of the sensor's own parameters or environmental factors, thereby making the measured value of the sensor more realistic.

[0077] Step 5: Obtain the trustworthiness of each neighboring sensor according to the measurement value after data cleaning;

[0078] When multiple sensors measure the same environmental parameter, it is assumed that the data collected by the mth sensor and the nth sensor at the same time are Ti and Tj, and the Ti and Tj data are related. In order to reflect the deviation between Ti and Tj, the present invention uses the variance of the data collected by the sensor to obtain the trust of each neighboring sensor.

[0079] Step 6: Obtain a trust matrix between each sensor according to the trust of each neighboring sensor; specifically, the formula is:

[0080]

[0081] Construct a trust matrix; where d m,n (m,n=1,2,…k) represents the trust between the sensor at point m and the sensor at point n, d m,n =|Q m -Q n |, Q m represents the variance of the data collected by the sensor at point m, Q n Represents the variance of the data collected by the sensors at point n.

[0082] Step 7: Obtain a fusion matrix according to the trust matrix between the sensors;

[0083] Furthermore, step 7 includes:

[0084] Step 7.1: Obtain a limit value; wherein the limit value ranges from [0.5-0.75].

[0085] Step 7.2: Construct a fusion matrix according to the limit value and the trust matrix; wherein the fusion matrix is:

[0086]

[0087]

[0088] Among them, α ij Indicates the limit value.

[0089] Step 8: Using the fusion matrix to fuse the measurement values ​​collected by each neighboring sensor to obtain a fused measurement value;

[0090] In the present invention, the step 8 specifically includes:

[0091] Step 8.1: Take the column or row with the most 1 values ​​in the fusion matrix as the preferred set;

[0092] Step 8.2: taking the measured values ​​of the sensors corresponding to the values ​​of 1 in the preferred set as the fusion set;

[0093] Step 8.3: Obtain a fused measurement value according to the fusion set; wherein the calculation formula of the fused measurement value is:

[0094]

[0095] Among them, T i is the i-th measurement value in the fusion set, and L is the number of elements in the fusion set.

[0096] The present invention selects the measurement values ​​to be fused based on the trust between each neighboring sensor, which can greatly increase the credibility of the data.

[0097] Step 9: Deploy the optimally positioned sensors at the preset safety monitoring points based on the fused measurement values.

[0098] Further, the step 9 comprises:

[0099] Step 9.1: Randomly deploy new sensors around the preset safety monitoring points;

[0100] Step 9.2: Determine whether the absolute value of the difference between the new sensor's measurement value and the fused measurement value is greater than a preset threshold;

[0101] Step 9.3: If it is greater than the preset threshold, return to step 8.1;

[0102] Step 9.4: If it is less than the preset threshold, the current position of the new sensor is used as the optimal placement position of the sensor.

[0103] The present invention discloses a method for deploying safety monitoring sensors without blind spots, including: using an adaptive denoising function to remove abnormal values ​​in the measurement values ​​of each neighboring sensor to generate a measurement value after data cleaning; obtaining the trust of each neighboring sensor according to the measurement value after data cleaning; obtaining a fusion matrix between each sensor according to the trust of each neighboring sensor; using the fusion matrix to fuse the measurement values ​​collected by each neighboring sensor to obtain a fused measurement value; and deploying the sensor with the best position at a preset safety monitoring point according to the fused measurement value. The present invention finds the optimal monitoring position of a safety monitoring point by using the measurement values ​​after fusion of multiple sensors, and uses a new sensor to replace multiple sensors to collect environmental parameters of the safety monitoring point, which can ensure full coverage of the sensor network and solve the problem of cost increase and resource waste caused by too many sensors.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for deploying safety monitoring sensors without blind spots. It is characterized in that include: Step 1: Place multiple neighboring sensors at preset safety monitoring points; Step 2: Construct a measurement space model based on the distances between each neighboring sensor; The step 2: constructing a measurement space model according to the distances between each neighboring sensor, includes: Using the formula: Construct a measurement space model; wherein σ represents the average value of the difference between the sensor at point m and the sensor at point n within a preset time period, dis(m,n) represents the distance between the sensor at point m and the sensor at point n, and R represents an adjustable parameter; Step 3: Construct an adaptive denoising function based on the measurement space model; The step 3: constructing an adaptive denoising function according to the measurement space model, comprises: Step 3.1: Construct a denoising threshold according to the weighted average of the measured values; wherein the denoising threshold is: Among them, Y i represents the i-th measurement value collected by the sensor, W i Represents Y i The weight value of Step 3.2: constructing an adaptive denoising function according to the adaptive denoising threshold and the measurement space model; The adaptive denoising function is: Among them, x(m,t) represents the measurement value of the sensor at point m at time t, x(n,t) represents the measurement value of the sensor at point n at time t, ρ represents the equilibrium threshold, |N m | represents the number of neighboring sensors, Step 4: using the adaptive denoising function to remove abnormal values ​​in the measurement values ​​of each neighboring sensor to generate measurement values ​​after data cleaning; Step 5: Obtain the trustworthiness of each neighboring sensor according to the measurement value after data cleaning; Step 6: Obtain a trust matrix between each sensor according to the trust of each neighboring sensor; The step 6: obtaining a trust matrix between each sensor according to the trust of each neighboring sensor, includes: Using the formula: Construct a trust matrix; where d m,n represents the trust between the sensor at point m and the sensor at point n, and m,n=1,2,…k,d m,n =|Q m -Q n |, Q m represents the variance of the data collected by the sensor at point m, Q n Represents the variance of the data collected by the sensor at point n; Step 7: Obtain a fusion matrix according to the trust matrix between the sensors; The step 7: obtaining a fusion matrix according to the trust matrix between the sensors, includes: Step 7.1: Get the limit value; Step 7.2: Construct a fusion matrix according to the limit value and the trust matrix; wherein the fusion matrix is: Among them, α represents the limit value; Step 8: Using the fusion matrix to fuse the measurement values ​​collected by each neighboring sensor to obtain a fused measurement value; The step 8: using the fusion matrix to fuse the measurement values ​​collected by each neighboring sensor to obtain a fused measurement value, includes: Step 8.1: Take the column or row with the most 1 values ​​in the fusion matrix as the preferred set; Step 8.2: taking the measured values ​​of the sensors corresponding to the values ​​of 1 in the preferred set as the fusion set; Step 8.3: Obtain the fused measurement value according to the fusion set; wherein the calculation formula of the fused measurement value is: Among them, T c is the cth measurement value in the fusion set, L is the number of elements in the fusion set; Step 9: Deploy the optimally positioned sensors at the preset safety monitoring points according to the fused measurement values; The step 9: deploying the optimally positioned sensor at the preset safety monitoring point according to the fused measurement values, comprises: Step 9.1: Randomly deploy new sensors around the preset safety monitoring points; Step 9.2: Determine whether the absolute value of the difference between the new sensor's measurement value and the fused measurement value is greater than a preset threshold; Step 9.3: If it is greater than the preset threshold, return to step 9.1; Step 9.4: If it is less than the preset threshold, the current position of the new sensor is used as the optimal placement position of the sensor.

2. A method for deploying safety monitoring sensors without blind spots as claimed in claim 1, It is characterized in that The limit value ranges from [0.5, 0.75].

Images