Temperature sensor positioning method and system

Abstract

The present invention belongs to the field of data processing and relates to a temperature sensor positioning method and system, comprising: S1, obtaining the position coordinates and temperature data of each temperature measurement point of each search sample based on multiple acquired search samples; S2, obtaining the spatiotemporal fitness function value of each search sample; S3, determining whether the number of iterations has reached the maximum number of iterations; if the number of iterations has not reached the maximum number of iterations, updating the position coordinates of each temperature measurement point of each search sample using the OpenAI ES algorithm and re-executing step S2; if the number of iterations has reached the maximum number of iterations, terminating the iterations and outputting the position coordinates of each temperature measurement point of the search sample with the maximum spatiotemporal fitness function value. The present invention solves the problem of unscientific and unreasonable placement of temperature sensors in concrete dams.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and particularly discloses a temperature sensor positioning method and system. Background Art

[0002] The internal stress and strain characteristics of concrete change with the change of concrete temperature. When the temperature difference between different areas is large, the internal tensile stress of concrete may exceed the tensile strength and cause concrete cracking. Therefore, understanding the law of concrete temperature change is of great significance to preventing concrete cracking.

[0003] Concrete dam projects typically use temperature sensors embedded within the concrete to monitor concrete temperature in real time and analyze its temperature variations. The number of temperature sensors required is limited by cost and construction schedule constraints. Furthermore, temperatures in different parts of the concrete are correlated, and overcrowding can lead to data redundancy and inefficient monitoring. Therefore, a limited number of temperature sensors are typically embedded within concrete dams or concrete blocks. Scientifically and rationally deploying a limited number of temperature sensors throughout the entire area of a proposed concrete dam or concrete block is crucial for accurately reconstructing the concrete temperature field and accurately revealing its temperature variations.

[0004] Existing temperature sensor placement methods have the following shortcomings: they focus on monitoring the temperature of specific characteristic points without considering the accuracy of the temperature field; they determine the temperature sensor location based on the temperature field at a specific moment, which may not be representative; and they are mostly applied to research fields such as bridges, machinery, and greenhouses, but lack application in concrete dams or concrete blocks, especially arch dams. Therefore, conducting research on optimizing temperature sensor placement is of great significance to solving the problem of relying on experience to place temperature sensors in concrete dams and achieving a scientific and reasonable placement of temperature sensors. Summary of the Invention

[0005] The purpose of the present invention is to provide a temperature sensor positioning method and system to solve the problem that the arrangement of temperature sensors in concrete dams is not scientific and reasonable.

[0006] The specific scheme of the present invention is as follows:

[0007] A temperature sensor positioning method comprises the following steps:

[0008] S1. Obtaining the position coordinates of each temperature measurement point of each search sample and the temperature data of each temperature measurement point based on the obtained multiple search samples;

[0009] S2. Obtaining the spatiotemporal fitness function value of each search sample according to the position coordinates of each temperature measurement point of each search sample, the temperature data of each temperature measurement point, and the obtained position coordinates of each temperature data point;

[0010] S3. Determine whether the number of iterations has reached the maximum number of iterations. When the number of iterations has not reached the maximum number of iterations, update the position coordinates of each temperature measurement point of each search sample through the OpenAI ES algorithm, and re-execute step S2. When the number of iterations reaches the maximum number of iterations, end the iteration and output the position coordinates of each temperature measurement point of the search sample with the largest spatiotemporal fitness function value.

[0011] In some embodiments, obtaining the position coordinates of each temperature measurement point of each search sample includes:

[0012] Obtain Gaussian noise and obtain initial temperature measurement point parameters of each search sample;

[0013] The position coordinates of each temperature measurement point of each search sample are updated respectively according to the Gaussian noise and the initial temperature measurement point parameters of each search sample.

[0014] In some embodiments, obtaining the initial temperature measurement point parameters of each search sample includes:

[0015] Obtain multiple temperature measurement points of each search sample;

[0016] The probability of each temperature measurement point of each search sample being selected is set, and the probability of each temperature measurement point being selected of the same search sample is formed into a set of row vector data to generate the initial temperature measurement point parameters of each search sample respectively.

[0017] In some embodiments, updating the position coordinates of each temperature measurement point of each search sample according to Gaussian noise and the initial temperature measurement point parameters of each search sample includes:

[0018] Add Gaussian noise to each search sample;

[0019] The position coordinates of each temperature measurement point of each search sample are updated respectively according to the initial temperature measurement point parameters of each search sample.

[0020] In some embodiments, the acquired position coordinates of each temperature data point include:

[0021] The obtained initial temperature field is discretized according to the set interval to obtain multiple temperature data points;

[0022] The position coordinates of each temperature data point are obtained based on each temperature data point.

[0023] In some embodiments, obtaining the spatiotemporal fitness function value of each search sample includes:

[0024] S21, obtaining a normalized time fitness function value and a normalized space fitness function value of each search sample according to the temperature data of each temperature measurement point of each search sample;

[0025] S22, obtaining the dispersion index fitness function value of each search sample based on the position coordinates of each temperature data point and the position coordinates of each temperature measurement point of each search sample;

[0026] S23 , obtaining the spatiotemporal fitness function value of each search sample according to the normalized time fitness function value, the normalized space fitness function value, and the dispersion index fitness function value of each search sample.

[0027] In some embodiments, obtaining a normalized temporal fitness function value and a normalized spatial fitness function value of each search sample includes:

[0028] According to the temperature data of each temperature measurement point of each search sample, the time fitness function value and the space fitness function value of each search sample are obtained respectively;

[0029] The time fitness function value and the space fitness function value of each search sample are normalized respectively to obtain the normalized time fitness function value and the normalized space fitness function value of each search sample.

[0030] In some embodiments, obtaining the spatiotemporal fitness function value of each search sample according to the normalized temporal fitness function value, the normalized spatial fitness function value, and the dispersion index fitness function value of each search sample includes:

[0031] Set the ratio of time fitness, space fitness, and dispersion index fitness of each search sample;

[0032] The spatiotemporal fitness function value of each search sample is obtained according to the ratio of the temporal fitness, spatial fitness and dispersion index fitness of each search sample, as well as the normalized temporal fitness function value, normalized spatial fitness function value and dispersion index fitness function value of each search sample.

[0033] In some embodiments, the OpenAI ES algorithm is used to update the position coordinates of each temperature measurement point of each search sample, including:

[0034] Based on the OpenAI ES algorithm, the fitness gradient value of each search sample is obtained by obtaining Gaussian noise;

[0035] According to the fitness gradient value of each search sample, the temperature measurement point parameters of each search sample are updated separately using the gradient ascent method in the OpenAI ES algorithm;

[0036] The position coordinates of each temperature measurement point of each search sample are updated based on the temperature measurement point parameters of each search sample.

[0037] The present invention also relates to a temperature sensor positioning system, which is used in the above-mentioned temperature sensor positioning method, comprising:

[0038] Data acquisition module, used for collecting data information;

[0039] A spatiotemporal fitness function value calculation module is used to obtain the spatiotemporal fitness function value of each search sample based on the temperature data of each temperature measurement point of each search sample and the position coordinates of each temperature measurement point, as well as the obtained position coordinates of each temperature data point;

[0040] An iterative update module is used to update the position coordinates of each temperature measurement point of each search sample through the OpenAI ES algorithm, and to update the spatiotemporal fitness function value of each search sample based on the updated position coordinates of each temperature measurement point of each search sample and the temperature data of each temperature measurement point;

[0041] The temperature measurement point position generation module is used to determine whether the number of iterations has reached the maximum number of iterations. When the number of iterations has not reached the maximum number of iterations, the iteration continues; when the number of iterations has reached the maximum number of iterations, the iteration ends and the position coordinates of each temperature measurement point of the search sample with the largest spatiotemporal fitness function value are output.

[0042] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0043] By considering the spatiotemporal variation characteristics and dispersion index of the concrete dam temperature, and based on the spatiotemporal fitness function value of the characteristic time period, the OpenAI ES algorithm is used to obtain the optimal number and location of buried temperature sensors, thereby optimizing the layout of concrete dam temperature sensors, improving the accuracy of the temperature field, reducing redundant temperature sensors, and maximizing the use of monitoring data from each temperature sensor, thereby improving temperature monitoring efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a temperature sensor positioning method in Example 1 of the present invention.

[0045] Figure 2 This is a block diagram of a temperature sensor positioning system in Example 1 of the present invention. DETAILED DESCRIPTION

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0047] A temperature sensor positioning method, such as Figure 1 As shown, the following steps are included:

[0048] S1. Obtain the position coordinates of each temperature data point;

[0049] Based on the concrete dam or concrete block, an initial temperature field of the concrete dam or concrete block is obtained through a temperature field test method or a temperature field simulation method. The initial temperature field is a temperature field in a characteristic time period when the temperature changes drastically, and the characteristic time period includes n characteristic moments.

[0050] The initial temperature field is discretized according to a set interval to obtain multiple temperature data points. The set interval is usually 1 meter. The number of temperature data points is expressed as q, that is, q temperature data points are obtained.

[0051] The position coordinates of each temperature data point are obtained based on each temperature data point.

[0052] S2. Obtaining the initial temperature measurement point parameters of each search sample and the temperature data of each temperature measurement point;

[0053] Acquire multiple temperature measurement points of each search sample; set the probability of each temperature measurement point of each search sample being selected, form the probability of each temperature measurement point of the same search sample being selected into a group of row vector data, and generate initial temperature measurement point parameters of each search sample respectively; obtain temperature data of each temperature measurement point of each search sample according to each temperature measurement point of each search sample.

[0054] A plurality of search samples are obtained from the initial temperature field, and the number of search samples is expressed as λ, that is, λ search samples are obtained, and the λ search samples are standard normal distribution.

[0055] Multiple temperature measurement points of each search sample are obtained from each search sample, and the number of temperature measurement points in a single search sample is expressed as m, that is, m temperature measurement points are obtained for each search sample; the number of temperature measurement points is the number of temperature sensors that need to be arranged, and the position of each temperature measurement point is the position of each sensor that needs to be arranged; since the final temperature measurement point is obtained from the temperature data point through the OpenAI ES algorithm search, the number of temperature measurement points is less than the number of temperature data points, that is, m <q。

[0056] The initial temperature measurement point parameter θ0 refers to a set of row vector data consisting of the probability of each temperature measurement point being selected.

[0057] S3, obtaining the position coordinates of each temperature measurement point of each search sample;

[0058] Get Gaussian noise , where i=1, 2, 3, ..., m;

[0059] Add Gaussian noise to each search sample;

[0060] The position coordinates of each temperature measurement point of each search sample are updated respectively according to the initial temperature measurement point parameters of each search sample.

[0061] S4, obtaining the time fitness function value and the space fitness function value of each search sample according to the temperature data of each temperature measurement point of each search sample;

[0062] The time fitness function is used to reflect the degree of temperature change over time. The larger the time fitness function value, the more drastic the temperature change over time. The calculation formula of the time fitness function value is:

[0063] ,

[0064] in, is the time fitness function value; is the tth temperature measurement point at the i-th temperature measurement point j-1 Temperature data at the moment; is the tth temperature measurement point at the i-th temperature measurement point j Temperature data at the moment; n represents the characteristic time period; i=1, 2, 3, ..., m; j=1, 2, 3, ..., n.

[0065] The spatial fitness function is used to reflect the degree of temperature change over space. The larger the value of the spatial fitness function, the more drastic the temperature change over space. The calculation formula of the spatial fitness function value is:

[0066] ,

[0067] in, is the value of the spatial fitness function; For the tth j Temperature data of the kth adjacent temperature measurement point of the i-th temperature measurement point at the moment; is the tth temperature measurement point at the i-th temperature measurement point j The temperature data at the moment; l is the number of adjacent temperature measuring points around the i-th temperature measuring point. In actual calculation, the temperature measuring points within the radius of the first limit value with the i-th temperature measuring point as the center are regarded as the adjacent temperature measuring points of the i-th temperature measuring point. The first limit value is usually the set spacing. times, that is m;d k is the spatial distance between the i-th temperature measuring point and the k-th temperature measuring point adjacent to the i-th temperature measuring point; x i is the x-axis coordinate of the i-th temperature measurement point; k is the x-axis coordinate of the kth adjacent temperature measurement point of the i-th temperature measurement point; y i is the y-axis coordinate of the i-th temperature measurement point; k is the y-axis coordinate of the kth temperature measurement point adjacent to the i-th temperature measurement point; z i is the z-axis coordinate of the i-th temperature measurement point;k is the z-axis coordinate of the kth temperature measuring point adjacent to the ith temperature measuring point; i=1, 2, 3, ..., m; j=1, 2, 3, ..., n; k=1, 2, 3, ..., l.

[0068] S5. Normalizing the time fitness function value and the space fitness function value of each search sample to obtain a normalized time fitness function value and a normalized space fitness function value of each search sample;

[0069] Taking into account the different magnitudes of the temporal fitness function value and the spatial fitness function value, the temporal fitness function value and the spatial fitness function value are normalized respectively to obtain the normalized temporal fitness function value and the normalized spatial fitness function value.

[0070] The calculation formula of the normalized time fitness function value is:

[0071] ,

[0072] in, is the time fitness function value of a certain search sample; The maximum value of the time fitness function of all search samples; The minimum value of the time fitness function of all search samples; is the normalized time fitness function value of the current search sample.

[0073] The calculation formula of the normalized spatial fitness function value is:

[0074] ,

[0075] in, is the spatial fitness function value of a search sample; It is the maximum value of the spatial fitness function of all search samples; It is the minimum value of the spatial fitness function of all search samples; is the normalized spatial fitness function value of the current search sample.

[0076] S6. Obtaining the dispersion index fitness function value of each search sample based on the position coordinates of each temperature data point and the position coordinates of each temperature measurement point of each search sample;

[0077] The dispersion index fitness function is used to reflect the degree of dispersion among multiple temperature measurement points. The larger the dispersion index fitness function value, the more dispersed the locations of the temperature measurement points are, so as to avoid multiple temperature sensors gathering at a location with drastic temperature changes, resulting in redundant temperature monitoring information. The calculation formula of the dispersion index fitness function value is:

[0078] ,

[0079] in, is the fitness function value of the dispersion index of a search sample; d h is the spatial distance between the m temperature measurement points obtained from the current search sample, h = 1, 2, 3, ..., m(m-1) / 2; d p is the spatial distance between the q temperature data points in the initial temperature field, p = 1, 2, 3, ..., q (q-1) / 2; d max is the maximum value of the spatial distance between each temperature data point in the q temperature data points of the initial temperature field; is the ratio of the spatial distance between each temperature data point in the q temperature data points of the initial temperature field to the maximum value of the spatial distance between each temperature data point in the q temperature data points of the initial temperature field, The purpose is to map the fitness function value of the dispersion indicator to the range of 0~1, so as to construct the fitness function value of the temperature sensor together with the normalized time fitness function value and the normalized space fitness function value.

[0080] S7, obtaining the spatiotemporal fitness function value of each search sample according to the normalized time fitness function value, the normalized space fitness function value, and the dispersion index fitness function value of each search sample;

[0081] Set the ratio of time fitness, space fitness, and dispersion index fitness of each search sample;

[0082] The spatiotemporal fitness function value of each search sample is obtained according to the ratio of the temporal fitness, spatial fitness and dispersion index fitness of each search sample, as well as the normalized temporal fitness function value, normalized spatial fitness function value and dispersion index fitness function value of each search sample.

[0083] The ratio of temporal fitness, spatial fitness, and dispersion index fitness is customized as follows: temporal fitness: spatial fitness: dispersion index fitness = β:γ:δ, 0≤β≤1, 0≤γ≤1, 0≤δ≤1.

[0084] Taking into account the spatiotemporal variation characteristics and dispersion index of temperature, the spatiotemporal fitness function value of the temperature measurement point layout, that is, the spatiotemporal fitness function value of the temperature sensor layout, is obtained; the calculation formula of the spatiotemporal fitness function value is:

[0085] ,

[0086] in, is the spatiotemporal fitness function value of a search sample; is the normalized time fitness function value of the current search sample; β is the proportion of the time fitness of the current search sample; is the normalized spatial fitness function value of the current search sample; γ is the proportion of the spatial fitness of the current search sample; is the fitness function value of the dispersion index of the current search sample; δ is the proportion of the fitness function of the dispersion index of the current search sample.

[0087] S8. Determine whether the number of iterations has reached the maximum number of iterations. When the number of iterations has not reached the maximum number of iterations, update the position coordinates of each temperature measurement point of each search sample using the OpenAI ES algorithm, and re-execute steps S4 to S7. When the number of iterations reaches the maximum number of iterations, end the iteration and output the position coordinates of each temperature measurement point of the search sample with the largest spatiotemporal fitness function value.

[0088] Set the number of iterations, learning rate, and Gaussian noise standard deviation, and denote the maximum number of iterations as R.

[0089] Determine whether the number of iterations reaches the maximum number of iterations. When the number of iterations does not reach the maximum number of iterations, obtain the fitness gradient value of each search sample through Gaussian noise based on the OpenAI ES algorithm; update the temperature measurement point parameters of each search sample based on the fitness gradient value of each search sample using the gradient ascent method in the OpenAI ES algorithm; update the position coordinates of each temperature measurement point of each search sample based on the temperature measurement point parameters of each search sample, and re-execute steps S4 to S7, that is, update the spatiotemporal fitness function value of each search sample based on the updated position coordinates of each temperature measurement point of each search sample and the temperature data of each temperature measurement point;

[0090] When the number of iterations reaches the maximum number of iterations, the iteration ends, the search sample with the largest value of the spatiotemporal fitness function is obtained, and the position coordinates of each temperature measurement point of the search sample with the largest value of the spatiotemporal fitness function are output, that is, the position coordinates of each temperature sensor with the optimal arrangement are obtained.

[0091] The calculation formula of the fitness gradient value is:

[0092] ,

[0093] in, is the fitness gradient value, σ is the Gaussian noise standard deviation, is Gaussian noise, θ is the current temperature measurement point parameter, For expectations, is the fitness function.

[0094] The calculation formula for updating the temperature measurement point parameters is:

[0095] ,

[0096] in, is the temperature measurement point parameter after update, θ is the temperature measurement point parameter before update, α is the learning rate, σ is the Gaussian noise standard deviation, is Gaussian noise, For expectations, is the fitness function.

[0097] By considering the spatiotemporal variation characteristics and dispersion index of the concrete dam temperature, and based on the spatiotemporal fitness function value of the characteristic time period, the OpenAI ES algorithm is used to obtain the optimal number and location of buried temperature sensors, thereby optimizing the layout of concrete dam temperature sensors, improving the accuracy of the temperature field, reducing redundant temperature sensors, and maximizing the use of monitoring data from each temperature sensor, thereby improving temperature monitoring efficiency.

[0098] The present invention also relates to a temperature sensor positioning system, which is used in the above-mentioned temperature sensor positioning method, such as Figure 2 Shown, including:

[0099] a data acquisition module, for collecting data information, the data information including an initial temperature field, multiple temperature data points, position coordinates of each temperature data point, multiple search samples, multiple temperature measurement points of each search sample, temperature measurement point parameters of each search sample, temperature data of each temperature measurement point of each search sample, position coordinates of each temperature measurement point of each search sample, a time fitness function value of each search sample, a spatial fitness function value of each search sample, a normalized time fitness function value of each search sample, a normalized spatial fitness function value of each search sample, a dispersion index fitness function value of each search sample, a spatiotemporal fitness function value of each search sample, and a fitness gradient value of each search sample;

[0100] A spatiotemporal fitness function value calculation module is used to obtain the spatiotemporal fitness function value of each search sample based on the temperature data of each temperature measurement point of each search sample and the position coordinates of each temperature measurement point, as well as the obtained position coordinates of each temperature data point;

[0101] An iterative update module is used to update the position coordinates of each temperature measurement point of each search sample through the OpenAI ES algorithm, and to update the spatiotemporal fitness function value of each search sample based on the updated position coordinates of each temperature measurement point of each search sample and the temperature data of each temperature measurement point;

[0102] The temperature measurement point position generation module is used to determine whether the number of iterations has reached the maximum number of iterations. When the number of iterations has not reached the maximum number of iterations, the iteration continues; when the number of iterations has reached the maximum number of iterations, the iteration ends and the position coordinates of each temperature measurement point of the search sample with the largest spatiotemporal fitness function value are output.

[0103] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A temperature sensor positioning method, characterized in that: The following steps are involved: S1. Obtaining the position coordinates of each temperature measurement point of each search sample and the temperature data of each temperature measurement point based on the obtained multiple search samples; S2. Obtaining the spatiotemporal fitness function value of each search sample according to the position coordinates of each temperature measurement point of each search sample, the temperature data of each temperature measurement point, and the obtained position coordinates of each temperature data point; The obtained position coordinates of each temperature data point include: based on the concrete dam or concrete block, obtaining the initial temperature field of the concrete dam or concrete block through a temperature field test method or a temperature field simulation method; the initial temperature field is the temperature field of a characteristic time period with drastic temperature changes; The obtaining of the spatiotemporal fitness function value of each search sample comprises: obtaining a time fitness function value and a space fitness function value of each search sample according to the temperature data of each temperature measuring point of each search sample, wherein the time fitness function is used to reflect the degree of change of temperature over time, and a larger value of the time fitness function indicates that the temperature changes more drastically over time; the space fitness function is used to reflect the degree of change of temperature over space, and a larger value of the space fitness function indicates that the temperature changes more drastically over space; the space fitness function value is related to the temperature data of a temperature measuring point at a certain moment, the temperature data of adjacent temperature measuring points, and the spatial distance between a temperature measuring point and adjacent temperature measuring points; obtaining a dispersion index fitness function value of each search sample based on the position coordinates of each temperature data point and the position coordinates of each temperature measuring point of each search sample, wherein the dispersion index fitness function is used to reflect the degree of dispersion between a plurality of temperature measuring points, and a larger value of the dispersion index fitness function indicates that the positions of the temperature measuring points are more dispersed; S3. Determine whether the number of iterations reaches the maximum number of iterations. When the number of iterations does not reach the maximum number of iterations, update the position coordinates of each temperature measurement point of each search sample using the OpenAIES algorithm, and re-execute step S2. When the number of iterations reaches the maximum number of iterations, end the iteration and output the position coordinates of each temperature measurement point of the search sample with the largest spatiotemporal fitness function value.

2. A temperature sensor positioning method according to claim 1, characterized in that: The step of obtaining the position coordinates of each temperature measurement point of each search sample includes: Obtain Gaussian noise and obtain initial temperature measurement point parameters of each search sample; The position coordinates of each temperature measurement point of each search sample are updated respectively according to the Gaussian noise and the initial temperature measurement point parameters of each search sample.

3. A temperature sensor positioning method according to claim 2, characterized in that: The step of obtaining the initial temperature measurement point parameters of each search sample includes: Obtain multiple temperature measurement points of each search sample; The probability of each temperature measurement point of each search sample being selected is set, and the probability of each temperature measurement point being selected of the same search sample is formed into a set of row vector data to generate the initial temperature measurement point parameters of each search sample respectively.

4. A temperature sensor positioning method according to claim 2, characterized in that: The updating of the position coordinates of each temperature measurement point of each search sample according to the Gaussian noise and the initial temperature measurement point parameters of each search sample comprises: Add Gaussian noise to each search sample; The position coordinates of each temperature measurement point of each search sample are updated respectively according to the initial temperature measurement point parameters of each search sample.

5. A temperature sensor positioning method according to claim 1, characterized in that: The acquired position coordinates of each temperature data point include: The obtained initial temperature field is discretized according to a set interval to obtain a plurality of temperature data points; and the position coordinates of each temperature data point are obtained based on each temperature data point.

6. A temperature sensor positioning method according to claim 1, characterized in that: The step of obtaining the spatiotemporal fitness function value of each search sample includes: S21, obtaining a normalized time fitness function value and a normalized space fitness function value of each search sample according to the temperature data of each temperature measurement point of each search sample; S22, obtaining the dispersion index fitness function value of each search sample based on the position coordinates of each temperature data point and the position coordinates of each temperature measurement point of each search sample; S23 , obtaining the spatiotemporal fitness function value of each search sample according to the normalized time fitness function value, the normalized space fitness function value, and the dispersion index fitness function value of each search sample.

7. A temperature sensor positioning method according to claim 6, characterized in that: The obtaining of the normalized time fitness function value and the normalized space fitness function value of each search sample includes: According to the temperature data of each temperature measurement point of each search sample, the time fitness function value and the space fitness function value of each search sample are obtained respectively; The time fitness function value and the space fitness function value of each search sample are normalized respectively to obtain the normalized time fitness function value and the normalized space fitness function value of each search sample.

8. A temperature sensor positioning method according to claim 6, characterized in that: The step of obtaining the spatiotemporal fitness function value of each search sample according to the normalized time fitness function value, the normalized space fitness function value, and the dispersion index fitness function value of each search sample comprises: Set the ratio of time fitness, space fitness, and dispersion index fitness of each search sample; The spatiotemporal fitness function value of each search sample is obtained according to the ratio of the temporal fitness, spatial fitness and dispersion index fitness of each search sample, as well as the normalized temporal fitness function value, normalized spatial fitness function value and dispersion index fitness function value of each search sample.

9. A temperature sensor positioning method according to claim 1, characterized in that: The updating of the position coordinates of each temperature measurement point of each search sample by the OpenAIES algorithm includes: Based on the OpenAIES algorithm, the fitness gradient value of each search sample is obtained by obtaining Gaussian noise; According to the fitness gradient value of each search sample, the temperature measurement point parameters of each search sample are updated respectively through the gradient ascent method in the OpenAIES algorithm; The position coordinates of each temperature measurement point of each search sample are updated based on the temperature measurement point parameters of each search sample.

10. A temperature sensor positioning system, characterized in that: A temperature sensor positioning method according to any one of claims 1 to 9, comprising: Data acquisition module, used for collecting data information; A spatiotemporal fitness function value calculation module is used to obtain the spatiotemporal fitness function value of each search sample based on the temperature data of each temperature measurement point of each search sample and the position coordinates of each temperature measurement point, as well as the obtained position coordinates of each temperature data point; An iterative update module is used to update the position coordinates of each temperature measurement point of each search sample through the OpenAIES algorithm, and update the spatiotemporal fitness function value of each search sample based on the updated position coordinates of each temperature measurement point of each search sample and the temperature data of each temperature measurement point; The temperature measurement point position generation module is used to determine whether the number of iterations has reached the maximum number of iterations. When the number of iterations has not reached the maximum number of iterations, the iteration continues; when the number of iterations has reached the maximum number of iterations, the iteration ends and the position coordinates of each temperature measurement point of the search sample with the largest spatiotemporal fitness function value are output.

Images