ITO touch signal dynamic threshold adjusting method based on fuzzy control

Abstract

The invention discloses an ITO touch signal dynamic threshold adjustment method based on fuzzy control, and relates to the technical field of intelligent touch adjustment, ITO touch signals and environmental noise are collected and preprocessed, and effective characteristics including touch signal intensity, change rate and environmental noise intensity are obtained; designing a fuzzy controller, selecting the touch signal intensity, the change rate and the environmental noise intensity as input variables, and fuzzifying the input variables into a membership function; the fuzzy control method is combined with multiple factors such as the touch signal intensity, the change rate and the environmental noise intensity, the touch signal detection threshold value is dynamically adjusted, effective touch signals and noise signals are effectively distinguished, the conditions of misjudgment and missed judgment can be reduced, the accuracy of touch detection is improved, and the user experience is improved. Particularly, when the touch force or environmental noise suddenly changes, the touch signal can be quickly adapted and accurately recognized, and the accuracy and reliability of user operation are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent touch control adjustment, and particularly relates to a method for dynamically adjusting the threshold of ITO touch signals based on fuzzy control. Background Art

[0002] ITO (Indium Tin Oxide) is a commonly used transparent conductive material in touch screens. It senses touch signals based on the principle of capacitance change. When a user touches the touch screen, the electric field changes, generating a capacitance signal that can be detected by the sensor. In a capacitive touch screen, the processing of touch signals involves multiple steps, including signal acquisition, amplification, filtering, A / D conversion, and coordinate calculation. Due to the diversity of touch environments and noise interference, the intensity and quality of touch signals will change, which requires the touch control system to dynamically adjust the threshold to adapt to different situations. Therefore, to ensure the accurate recognition of touch signals, the screen needs to set an appropriate threshold to distinguish between the "touch" and "non-touch" states.

[0003] In the prior art, it is difficult to accurately distinguish effective touch signals and noise signals in ITO touch signal adjustment, and false positives or false negatives are likely to occur. Moreover, when the touch force or environmental noise suddenly changes, it is unable to quickly adapt to the change of touch signals. Therefore, how to combine fuzzy control and fruit fly algorithm to dynamically adjust the threshold, adapt to the change of touch signals and environmental noise, and optimize the parameters of fuzzy control rules to improve the response speed and accuracy is the problem to be solved by the present invention. For this purpose, a method for dynamically adjusting the threshold of ITO touch signals based on fuzzy control is proposed. [[ID=1s3]]Summary of the Invention

[0004] The purpose of the present invention is to provide a method for dynamically adjusting the threshold of ITO touch signals based on fuzzy control to solve the problems raised in the above background art.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A method for dynamically adjusting the threshold of ITO touch signals based on fuzzy control includes the following steps:

[0007] S1. Collect ITO touch signals and environmental noise and perform preprocessing to obtain effective features, including touch signal intensity, change rate, and environmental noise intensity;

[0008] S2. Design a fuzzy controller, select touch signal intensity, change rate, and environmental noise intensity as input variables, and fuzzify them into membership functions;

[0009] S3. According to the dynamic changes of touch signals and environmental noise, formulate a fuzzy rule base and define fuzzy language variables;

[0010] S4. Through the fuzzy inference mechanism, dynamically adjust the touch signal detection threshold according to the fuzzy values of the input variables, and obtain the precise touch signal detection threshold through defuzzification;

[0011] S5. Use the fruit fly algorithm to optimize the membership functions and fuzzy rules of the fuzzy controller, search for the optimal threshold adjustment strategy, optimize the parameters of the fuzzy control rules through the fruit fly algorithm, and minimize the misjudgment and miss judgment rates;

[0012] S6. According to the optimization results of the fuzzy controller and the fruit fly algorithm, update the touch signal detection threshold in real time, and verify its performance in ITO touch under different touch environments and noises.

[0013] A further improvement of the technical solution of the present invention lies in: The S1 specifically includes:

[0014] Collect the original touch signal data through the sensing layer of the ITO touch screen, and use the environmental noise sensor to capture the synchronous environmental noise data. After the collection is completed, store the touch signal and the environmental noise data in different data channels respectively. Among them, the touch signal is manifested as the change of capacitance or resistance, and the environmental noise comes from electromagnetic interference or radio frequency interference;

[0015] Preprocess the collected touch signal and environmental noise data, including filtering and denoising operations, and perform normalization processing on the touch signal and environmental noise data to scale the data to the same magnitude and eliminate the dimension difference;

[0016] Extract the effective features from the preprocessed touch signal and environmental noise data, including the touch signal strength, change rate, and environmental noise strength, and integrate the extracted touch signal strength, change rate, and environmental noise strength into a feature vector.

[0017] A further improvement of the technical solution of the present invention lies in: The S2 specifically includes:

[0018] Design a fuzzy controller, and clarify the input variables of the fuzzifier. Among them, the input variables of the fuzzy controller are the touch signal strength, change rate, and environmental noise strength. For the three input variables, design the corresponding fuzzification strategies. Divide the touch signal strength into three fuzzy sets: weak, medium, and strong to comprehensively reflect the change of touch force. Divide the change rate into three fuzzy sets: slow, medium, and fast to accurately describe different levels of touch speed. Divide the environmental noise strength into three fuzzy sets: low, medium, and high;

[0019] Based on the characteristics of the input variables and actual needs, a membership function is constructed for each fuzzy set. For touch signal strength, a Gaussian membership function is used. For change rate, a triangular membership function is used. Its sharp turning point can clearly distinguish the boundaries between different rates. A trapezoidal membership function is used for ambient noise intensity.

[0020] Determine the domain of each input variable, that is, the range of values of the input variable, and divide the domain into several fuzzy subsets, each subset corresponds to a fuzzy set, to ensure that the membership function can cover the entire domain, and then set the parameters of the membership function to complete the construction of the membership function.

[0021] A further improvement of the technical solution of the present invention is that the domain of the input variable is set as follows:

[0022] The domain of each input variable is as follows: the domain range of the touch signal strength is [0,10], which means the strength of the touch signal ranges from zero to maximum;

[0023] The domain range of the change rate is [0,5], which means the change rate of the touch signal ranges from static to the fastest;

[0024] The domain range of ambient noise intensity is [0,8], which means the ambient noise intensity ranges from zero to maximum.

[0025] A further improvement of the technical solution of the present invention is that the parameters of the membership function are set as follows:

[0026] For touch signal strength:

[0027] The weak touch fuzzy set uses a Gaussian membership function, with the center point set at a lower position in the domain and a narrow width to cover the range of weak touch signal strength. The parameters are: center point 2, width 1.5. The medium touch fuzzy set uses a Gaussian membership function, with the center point located in the middle of the domain and a moderate width to cover the range of medium touch signal strength. The parameters are: center point 5, width 1.5. The strong touch fuzzy set uses a Gaussian membership function with the center point set at a higher position in the domain and a narrow width to cover the range of strong touch signal strength. The parameters are: center point 8, width 1.5.

[0028] For the rate of change:

[0029] The slow - changing fuzzy set uses a triangular membership function. The vertex is located at the starting part of the universe of discourse. The left boundary starts from the starting point of the universe of discourse, and the right boundary extends to the middle position, highlighting the boundary with a slower change rate. The parameters are: the vertex is at 1, the left boundary is 0, and the right boundary is 2. The medium - changing fuzzy set has the vertex of the triangular membership function located at the middle position of the universe of discourse. The left boundary starts from the right boundary of the slow - changing set, and the right boundary extends to the left boundary of the fast - changing set, clarifying the range with a medium change rate. The parameters are: the vertex is at 3, the left boundary is 2, and the right boundary is 4. The fast - changing fuzzy set has the vertex of the triangular membership function located at the end part of the universe of discourse. The left boundary starts from the right boundary of the medium - changing set, and the right boundary extends to the end point of the universe of discourse, emphasizing the boundary with a faster change rate. The parameters are: the vertex is at 5, the left boundary is 4, and the right boundary is 6;

[0030] For the environmental noise intensity:

[0031] The low - noise fuzzy set uses a trapezoidal membership function. The left bottom starts from the starting point of the universe of discourse. The left top and the right top are respectively located at the lower positions of the universe of discourse, and the right bottom extends to the middle position, adapting to the wide - range change of lower environmental noise intensity. The parameters are: the left bottom is 0, the left top is 2, the right top is 3, and the right bottom is 4. The medium - noise fuzzy set has the left bottom and the left top of the trapezoidal membership function respectively located at the middle position of the universe of discourse, and the right top and the right bottom respectively extend to the higher positions, covering the range of medium environmental noise intensity. The parameters are: the left bottom is 2, the left top is 4, the right top is 6, and the right bottom is 8. The high - noise fuzzy set has the left bottom and the left top of the trapezoidal membership function respectively located at the higher positions of the universe of discourse, and the right top and the right bottom extend to the end point of the universe of discourse, adapting to the wide - range change of higher environmental noise intensity. The parameters are: the left bottom is 5, the left top is 7, the right top is 8, and the right bottom is 10.

[0032] A further improvement of the technical solution of the present invention lies in that: S3 specifically includes:

[0033] Defining the touch - signal detection threshold as the output variable, and analyzing the relationships between the three input variables of touch - signal intensity, change rate, and environmental noise intensity and the output variable;

[0034] According to the fuzzy sets of the input variables, defining fuzzy linguistic variables. For the touch - signal intensity, the linguistic variables are defined as "weak", "medium", and "strong". For the change rate, the linguistic variables are defined as "slow", "medium", and "fast". For the environmental noise intensity, the linguistic variables are defined as "low", "medium", and "high". Each linguistic variable corresponds to a fuzzy set, and its fuzzy characteristics are described by the membership function. The linguistic variables will be used to construct fuzzy rules to express the fuzzy relationship between the input variables and the output variable;

[0035] Based on the relationship between the input variables and the output variables, the fuzzy rules are further refined. For each combination of the linguistic variables of the touch signal and the environmental noise, specific fuzzy rules are formulated to describe the output behavior of the system, that is, the adjustment method of the touch signal detection threshold. And the refined fuzzy rules are integrated into a fuzzy rule base to ensure that the rule base can comprehensively cover all possible input situations.

[0036] A further improvement of the technical solution of the present invention lies in that: the S4 specifically includes:

[0037] In the fuzzy inference mechanism, the parameters and structure of the fuzzy controller are initialized, including determining the universes of discourse of the input variables and the output variable, the fuzzy set partitioning, and the type of membership function. And the actual measured values of the three input variables of the touch signal strength, the change rate, and the environmental noise strength are converted into corresponding fuzzy values through the defined membership function.

[0038] The fuzzy values of the input variables are input into the fuzzy rule base for fuzzy inference. For each fuzzy rule, its activation degree is calculated according to the membership function of the input variables. For each rule, the membership values of the input variables are calculated, and the activation weight of the fuzzy rule is determined according to the fuzzy operation. Among them, the activation weight reflects the importance of the fuzzy rule under the current input conditions. According to the activation weights of all fuzzy rules, the fuzzy value of the output variable is calculated. The fuzzy value of the output variable is a fuzzy set, which describes the possible range of the touch signal detection threshold.

[0039] The fuzzy set of the output variable obtained by fuzzy inference is defuzzified through the defuzzification method, and the fuzzy value of the output variable is converted into an exact value to obtain the touch signal detection threshold, which is used to update the detection standard of the touch signal in real time.

[0040] A further improvement of the technical solution of the present invention lies in that: the calculation process of the fuzzy value of the output variable is as follows:

[0041] For each fuzzy rule, the membership values of the input variables are calculated, and the minimum value of the membership values of the input variables is taken as the activation weight.

[0042] For each fuzzy rule, considering the combined influence of the touch signal strength, the change rate, and the environmental noise strength on the touch signal detection threshold, the square root of the sum of the squares of the membership values of the input variables is calculated to obtain the comprehensive membership value.

[0043] The exponential function of the membership values of the input variables is calculated, the average value is obtained, and the natural logarithm is taken after adding 1 to the average value to obtain the logarithmic compression value, ensuring that the output value will not be too large, and at the same time retaining the sensitivity of the input variables to the output.

[0044] Multiply the activation weight of each fuzzy rule by the comprehensive membership degree value, sum them up and then divide by the sum of all activation weights to obtain a preliminary comprehensive fuzzy value, and multiply the preliminary comprehensive fuzzy value by the logarithmic compression value to obtain the fuzzy value of the output variable;

[0045] The calculation process of the touch signal detection threshold is as follows:

[0046] Calculate the sum of the membership degree values of each input variable in all fuzzy rules, and divide it by three times the number of fuzzy rules to obtain an average membership degree value;

[0047] Substitute the average membership degree value into the sine function to obtain a periodic adjustment factor;

[0048] Combine the calculated fuzzy value of the output variable with the periodic adjustment factor to calculate the final touch signal detection threshold.

[0049] A further improvement of the technical solution of the present invention lies in: the specific steps of S5 include:

[0050] Set the fruit fly algorithm and initialize the parameters of the fruit fly algorithm, including the population size (taking values between 20 and 100), the number of iterations (set between 100 and 1000), and the search range (determined according to the actual value ranges of the membership function parameters and the fuzzy rule weights), to ensure that the algorithm can comprehensively and efficiently search the solution space. At the same time, clarify the parameters to be optimized of the fuzzy controller, that is, the shape parameters of the membership function and the weight coefficients in the fuzzy rules, encode the parameters to be optimized as the position information of the fruit fly individuals, and each fruit fly individual represents a combination of the membership function and the fuzzy rules, and then randomly generate an initial fruit fly population to ensure the diversity and coverage of the population;

[0051] In the process of each iteration, the fruit fly algorithm calculates the corresponding fitness value according to the position information of the individual (that is, the membership function parameters and the fuzzy rule weights), and the fruit fly individuals search for a better position in the solution space through the olfactory and visual search mechanisms, that is, the combination of the membership function and the fuzzy rules that can reduce the misjudgment and missed judgment rates. After each iteration, update the position information of the fruit fly population, retain the individuals with higher fitness, and eliminate the individuals with lower fitness, gradually approaching the optimal solution;

[0052] After multiple iterations, the fruit fly algorithm converges to the optimal solution, that is, a set of optimal membership function parameters and fuzzy rule weight coefficients are obtained, and then they are applied to the fuzzy controller to form an optimal threshold adjustment strategy.

[0053] A further improvement of the technical solution of the present invention lies in: the specific steps of S6 include:

[0054] Based on the optimization results of the fuzzy controller and the fruit fly algorithm, the touch signal detection threshold is updated in real time. The optimized membership function parameters and fuzzy rule weight coefficients are applied to the fuzzy controller, enabling it to dynamically adjust the touch signal detection threshold according to the real-time measured values of the current touch signal strength, change rate, and environmental noise intensity.

[0055] Under different touch environments and noise conditions, the performance of the updated touch signal detection threshold is verified. Multiple experimental scenarios are designed to simulate different touch forces and environmental noise levels. In each experimental scenario, the touch detection results of the system are recorded, including the detection accuracy rate, false judgment rate, and missed judgment rate of the touch signal, to evaluate the stability and reliability of the system under different conditions.

[0056] According to the performance verification results, the parameters and rules of the system are further optimized to ensure that the system can quickly adapt to changes in touch force and environmental noise. If insufficient performance or slow adaptation speed is found during the verification process, the reasons need to be further analyzed, and the fruit fly algorithm is used again to fine-tune the fuzzy controller until the system performance meets the requirements.

[0057] Due to the adoption of the above technical solution, the technical progress achieved by the present invention compared with the prior art is:

[0058] 1. The present invention provides a method for dynamically adjusting the threshold of ITO touch signals based on fuzzy control. Through the fuzzy control method, considering multiple factors such as touch signal strength, change rate, and environmental noise intensity, the touch signal detection threshold is dynamically adjusted, effectively distinguishing valid touch signals from noise signals, reducing the situations of false judgment and missed judgment, improving the accuracy of touch detection. Especially when the touch force or environmental noise changes suddenly, it can quickly adapt and accurately identify touch signals, ensuring the accuracy and reliability of user operations.

[0059] 2. The present invention provides a method for dynamically adjusting the threshold of ITO touch signals based on fuzzy control. By continuously optimizing the membership function and fuzzy rules of the fuzzy controller, the system can maintain stable performance under different touch forces and environmental noise levels. The fruit fly algorithm is used to optimize the fuzzy controller, and the optimal membership function parameters and fuzzy rule weight coefficients can be found, thereby accelerating the speed of fuzzy reasoning, enabling the system to respond more quickly to changes in touch signals, adjust the detection threshold in real time, and improve the response speed and sensitivity of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0061] Figure 1 is a schematic diagram of the workflow of the present invention;

[0062] Figure 2 is a schematic diagram of the method flow of the present invention. Detailed implementation manners

[0063] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0064] Embodiment 1, as Figure 1 、 Figure 2 shown, the present invention provides a method for dynamically adjusting the threshold of ITO touch signals based on fuzzy control, including the following steps:

[0065] S1. Collect ITO touch signals and environmental noises and perform preprocessing to obtain effective features, including touch signal strength, change rate, and environmental noise strength. Collect the original touch signal data through the sensing layer of the ITO touch screen, and capture synchronous environmental noise data using an environmental noise sensor. After the collection is completed, store the touch signals and environmental noise data in different data channels respectively. Among them, the touch signal is manifested as a change in capacitance or resistance, and the environmental noise comes from electromagnetic interference or radio frequency interference. Perform preprocessing on the collected touch signals and environmental noise data, including filtering and denoising operations. Use a digital filter to remove high-frequency noise in the touch signal, effectively remove the high-frequency noise, and retain the effective information in the touch signal. For environmental noise, separate the noise components with frequencies similar to those of the touch signal through filtering processing to more accurately evaluate its impact on the touch signal, and perform normalization processing on the touch signal and environmental noise data to scale the data to the same magnitude and eliminate the dimension difference. Extract effective features from the preprocessed touch signals and environmental noise data, including touch signal strength, change rate, and environmental noise strength. Among them, for the touch signal, calculate its strength to quantify the touch force, and at the same time calculate the change rate to reflect the touch speed. For environmental noise, calculate its strength to evaluate the noise level, and integrate the extracted touch signal strength, change rate, and environmental noise strength into a feature vector. Each dimension of the feature vector corresponds to a feature value to ensure that the feature vector can comprehensively reflect the dynamic characteristics of the touch signal and environmental noise;

[0066] S2. Design a fuzzy controller. Select the touch signal strength, change rate, and ambient noise strength as input variables, and fuzzify them into membership functions. Design the fuzzy controller and clarify the input variables of the fuzzifier. Among them, the input variables of the fuzzy controller are the touch signal strength, change rate, and ambient noise strength. For the three input variables, design corresponding fuzzification strategies. Divide the touch signal strength into three fuzzy sets: weak, medium, and strong to comprehensively reflect the changes in touch force. The change rate is divided into three fuzzy sets: slow, medium, and fast to accurately describe different levels of touch speed. The ambient noise strength is divided into three fuzzy sets: low, medium, and high to effectively capture the differences in noise levels, ensuring that the fuzzy controller can handle various input situations in detail. According to the characteristics of the input variables and actual requirements, construct membership functions for each fuzzy set. For the touch signal strength, use a Gaussian membership function to describe the continuous change of touch intensity with its smooth characteristics. For the change rate, use a triangular membership function, and its sharp turning points can clearly distinguish the boundaries of different rates. For the ambient noise strength, select a trapezoidal membership function to adapt to the changes in noise strength over a wide range, ensuring that the membership function can flexibly cover various noise levels. Determine the universe of discourse of each input variable, that is, the range of values of the input variable, and divide the universe of discourse into several fuzzy subsets, each subset corresponding to a fuzzy set, ensuring that the membership function can cover the entire universe of discourse. Then, set the parameters of the membership function, that is, complete the construction of the membership function;

[0067] In addition, the universe of discourse of the input variables is set as follows:

[0068] Specifically, the universe of discourse of each input variable is: the universe of discourse range of the touch signal strength is [0, 10], indicating that the strength of the touch signal ranges from none to maximum; the universe of discourse range of the change rate is [0, 5], indicating that the change rate of the touch signal ranges from stationary to fastest; the universe of discourse range of the ambient noise strength is [0, 8], indicating that the ambient noise strength ranges from none to maximum;

[0069] Set the parameters of the membership function as follows:

[0070] For the touch signal strength: The weak touch fuzzy set uses a Gaussian membership function, with the center point set at a lower position in the universe of discourse and a narrower width to cover the range of weaker touch signal strength. The parameters are: the center point is 2, and the width is 1.5. The medium touch fuzzy set uses a Gaussian membership function, with the center point located in the middle of the universe of discourse and a moderate width to cover the range of medium touch signal strength. The parameters are: the center point is 5, and the width is 1.5. For the strong touch fuzzy set, the center point of the Gaussian membership function is set at a higher position in the universe of discourse and a narrower width to cover the range of stronger touch signal strength. The parameters are: the center point is 8, and the width is 1.5;

[0071] For the rate of change: For the slow - change fuzzy set, a triangular membership function is adopted. The vertex is located at the starting part of the universe of discourse. The left boundary starts from the starting point of the universe of discourse, and the right boundary extends to the middle position, highlighting the boundary with a slower rate of change. The parameters are: the vertex is at 1, the left boundary is 0, and the right boundary is 2. For the medium - change fuzzy set, the vertex of the triangular membership function is located at the middle position of the universe of discourse. The left boundary starts from the right boundary of the slow - change set, and the right boundary extends to the left boundary of the fast - change set, defining the range with a medium rate of change. The parameters are: the vertex is at 3, the left boundary is 2, and the right boundary is 4. For the fast - change fuzzy set, the vertex of the triangular membership function is located at the end part of the universe of discourse. The left boundary starts from the right boundary of the medium - change set, and the right boundary extends to the end point of the universe of discourse, emphasizing the boundary with a faster rate of change. The parameters are: the vertex is at 5, the left boundary is 4, and the right boundary is 6;

[0072] For the environmental noise intensity: For the low - noise fuzzy set, a trapezoidal membership function is adopted. The left bottom starts from the starting point of the universe of discourse. The left top and the right top are respectively located at the lower positions of the universe of discourse, and the right bottom extends to the middle position, adapting to the wide - range change of lower environmental noise intensity. The parameters are: the left bottom is 0, the left top is 2, the right top is 3, and the right bottom is 4. For the medium - noise fuzzy set, the left bottom and the left top of the trapezoidal membership function are respectively located at the middle positions of the universe of discourse, and the right top and the right bottom respectively extend to the higher positions, covering the range of medium environmental noise intensity. The parameters are: the left bottom is 2, the left top is 4, the right top is 6, and the right bottom is 8. For the high - noise fuzzy set, the left bottom and the left top of the trapezoidal membership function are respectively located at the higher positions of the universe of discourse, and the right top and the right bottom extend to the end point of the universe of discourse, adapting to the wide - range change of higher environmental noise intensity. The parameters are: the left bottom is 5, the left top is 7, the right top is 8, and the right bottom is 10;

[0073] S3. According to the dynamic changes of the touch signal and environmental noise, formulate a fuzzy rule base, define fuzzy linguistic variables, specify the touch signal detection threshold as the output variable, and analyze the relationships between the three input variables, i.e., the touch signal strength, change rate, and environmental noise strength, and the output variable. Among them, the touch signal strength reflects the touch force, the change rate reflects the touch speed, and the environmental noise strength reflects the level of surrounding interference. The touch signal detection threshold is jointly determined by the three input variables. When the touch signal strength is high, the touch signal detection threshold needs to be lowered to avoid missed detection. When the environmental noise strength is high, the touch signal detection threshold needs to be raised to avoid false detection. The change rate affects the dynamic adjustment of the touch signal detection threshold. A rapidly changing touch signal requires a more sensitive adjustment of the touch signal detection threshold. According to the fuzzy sets of the input variables, define fuzzy linguistic variables. For the touch signal strength, define the linguistic variables as "weak", "medium", and "strong". For the change rate, define the linguistic variables as "slow", "medium", and "fast". For the environmental noise strength, define the linguistic variables as "low", "medium", and "high". Each linguistic variable corresponds to a fuzzy set, and its fuzzy characteristics are described by the membership function. The linguistic variables will be used to construct fuzzy rules to express the fuzzy relationships between the input variables and the output variable. Based on the relationships between the input variables and the output variable, further refine the fuzzy rules. For each combination of the linguistic variables of the touch signal and environmental noise, formulate specific fuzzy rules to describe the output behavior of the system, i.e., the adjustment method of the touch signal detection threshold, and integrate the refined fuzzy rules into a fuzzy rule base to ensure that the rule base can comprehensively cover all possible input situations;

[0074] S4. Through the fuzzy inference mechanism, dynamically adjust the touch signal detection threshold according to the fuzzy values of the input variables, and obtain the precise touch signal detection threshold through defuzzification;

[0075] S6. Use the fruit fly algorithm to optimize the membership function and fuzzy rules of the fuzzy controller, search for the optimal threshold adjustment strategy, optimize the parameters of the fuzzy control rules through the fruit fly algorithm, and minimize the false detection and missed detection rates;

[0076] S6. According to the optimization results of the fuzzy controller and the fruit fly algorithm, update the touch signal detection threshold in real time, and verify its performance in ITO touch under different touch environments and noises to ensure that the system can quickly adapt to the changes in touch force and environmental noise.

[0077] Example 2, as Figure 1 、 Figure 2 shown, based on Example 1, the present invention provides a technical solution: Preferably, S4 specifically includes:

[0078] In the fuzzy inference mechanism, the parameters and structure of the fuzzy controller are initialized, including determining the universes of discourse of the input variables and output variables, the fuzzy set partitioning, and the type of membership functions. The actual measured values of the three input variables, i.e., the touch signal strength, the change rate, and the environmental noise strength, are converted into corresponding fuzzy values through the defined membership functions. The fuzzy values of the input variables are input into the fuzzy rule base for fuzzy inference. For each fuzzy rule, its activation degree is calculated according to the membership functions of the input variables. For each rule, the membership values of the input variables are calculated, and the activation weight of the fuzzy rule is determined according to the fuzzy operation. Among them, the activation weight reflects the importance of the fuzzy rule under the current input conditions. According to the activation weights of all fuzzy rules, the fuzzy value of the output variable is calculated. The fuzzy value of the output variable is a fuzzy set, which describes the possible range of the touch signal detection threshold. The fuzzy set of the output variable obtained by fuzzy inference is defuzzified through the defuzzification method, and the fuzzy value of the output variable is converted into an exact value to obtain the touch signal detection threshold for real-time updating the detection standard of the touch signal;

[0079] The calculation process of the fuzzy value of the output variable is as follows:

[0080] For each fuzzy rule, the membership values of the input variables are calculated, and the minimum value of the membership values of the input variables is taken as the activation weight. For each fuzzy rule, considering the combined influence of the touch signal strength, the change rate, and the environmental noise strength on the touch signal detection threshold, the square root of the sum of the squares of the membership values of the input variables is calculated to obtain the comprehensive membership value. The exponential function of the membership values of the input variables is calculated, and the average value is obtained. The natural logarithm is taken after adding 1 to the average value to obtain the logarithmic compression value, ensuring that the output value will not be too large while retaining the sensitivity of the input variables to the output. The activation weight of each fuzzy rule is multiplied by the comprehensive membership value, the sum is calculated and then divided by the sum of all activation weights to obtain the preliminary comprehensive fuzzy value, and the preliminary comprehensive fuzzy value is multiplied by the logarithmic compression value to obtain the fuzzy value of the output variable. The contributions of all rules are integrated to obtain the exact fuzzy value for subsequent defuzzification processing;

[0081] The calculation expression of the fuzzy value of the output variable is:

[0082]

[0083] w i =min(μ in，i ,μ ra，i ,μ no，i );

[0084] In the formula, μ output is the fuzzy value of the output variable, n is the number of fuzzy rules, w iis the activation weight of the i-th fuzzy rule, reflecting the importance of the rule under the current input conditions, μ in，i is the membership degree value of the touch signal strength in the i-th rule, with a value range of [0, 1]. When the touch signal strength increases, μ in，i will increase, μ ra，i is the membership degree value of the change rate in the i-th rule, with a value range of [0, 1]. When the change rate accelerates, μ ra，i will increase, μ no，i is the membership degree value of the environmental noise intensity in the i-th rule, with a value range of [0, 1]. When the environmental noise intensity increases, μ no，i will increase, is used to calculate the comprehensive membership degree value of the input variable, reflecting the comprehensive influence of the input variable in the i-th rule, and are used to exponentially amplify the membership degree value of the input variable to emphasize the influence of high membership degree values, is used to logarithmically compress the result of the exponential amplification to keep the output value within a reasonable range;

[0085] The calculation process of the touch signal detection threshold is as follows:

[0086] Calculate the sum of the membership degree values of each input variable in all fuzzy rules, divide it by three times the number of fuzzy rules to obtain an average membership degree value, substitute the average membership degree value into the sine function, and the parameter of the sine function is π / 2 multiplied by the average membership degree value to obtain a periodic adjustment factor. The value range of the periodic adjustment factor is [0, 1], which shows a periodic change trend according to the comprehensive membership degree value of the input variable, introducing a dynamic adjustment mechanism for the calculation of the touch signal detection threshold. Combine the calculated fuzzy value of the output variable with the periodic adjustment factor to calculate the final touch signal detection threshold;

[0087] The calculation expression of the touch signal detection threshold is:

[0088]

[0089] In the formula, T is the touch signal detection threshold, with a value range of [0, 10], representing the precise threshold for touch signal detection, used to update the detection standard in real time, is the periodic adjustment factor, used to perform periodic adjustment according to the comprehensive membership degree value of the input variable to make the output value have a certain volatility, with a value range of [0, 1]. When the comprehensive membership degree value of the input variable increases, the periodic adjustment factor first increases and then decreases, showing a sine wave form;

[0090] S5 specifically includes:

[0091] Set up the fruit fly algorithm and initialize the parameters of the fruit fly algorithm, including the population size (taking a value between 20 and 100), the number of iterations (set between 100 and 1000), and the search range (determined according to the actual value ranges of the membership function parameters and the fuzzy rule weights), to ensure that the algorithm can search the solution space comprehensively and efficiently. At the same time, clarify the parameters to be optimized of the fuzzy controller, that is, the shape parameters of the membership function and the weight coefficients in the fuzzy rules. Encode the parameters to be optimized as the position information of the fruit fly individuals. Each fruit fly individual represents a combination of a membership function and a fuzzy rule. Then randomly generate an initial fruit fly population to ensure the diversity and coverage of the population. During each iteration, the fruit fly algorithm calculates the corresponding fitness value according to the position information of the individual (i.e., the membership function parameters and the fuzzy rule weights). And the fruit fly individuals search for better positions in the solution space through the olfactory and visual search mechanisms, that is, the combination of the membership function and the fuzzy rule that can reduce the misjudgment and omission rates. After each iteration, update the position information of the fruit fly population, retain the individuals with higher fitness, and eliminate the individuals with lower fitness, gradually approaching the optimal solution. Among them, the fitness function is defined as the weighted sum of the misjudgment rate and the omission rate based on these two rates. The lower the fitness value, the better the performance of the parameter combination. The olfactory search is to make random moves within a local area with a small step size for fine search. The visual search is to make jump moves within a global range with a large range for exploring new areas. Through the combination of the two search mechanisms, the fruit fly individuals can effectively search for the parameter combination that can reduce the misjudgment and omission rates in the solution space. After multiple iterations, the fruit fly algorithm converges to the optimal solution, that is, a set of optimal membership function parameters and fuzzy rule weight coefficients are obtained. Then apply them to the fuzzy controller to form an optimal threshold adjustment strategy. Among them, after each iteration, update the position information of the fruit fly population, retain the individuals with higher fitness, and eliminate the individuals with lower fitness. When the set number of iterations is reached, the algorithm stops iterating. The position information of the final optimal fruit fly individual is the optimal membership function parameters and fuzzy rule weight coefficients of the fuzzy controller;

[0092] S6 specifically includes:

[0093] Based on the optimization results of the fuzzy controller and the fruit fly algorithm, the touch signal detection threshold is updated in real time. The optimized membership function parameters and fuzzy rule weight coefficients are applied to the fuzzy controller, enabling it to dynamically adjust the touch signal detection threshold according to the real-time measured values of the current touch signal intensity, change rate, and environmental noise intensity. Performance verification of the updated touch signal detection threshold is carried out under different touch environments and noise conditions. Multiple experimental scenarios are designed to simulate different touch forces and environmental noise levels. Under each experimental scenario, the touch detection results of the system are recorded, including the detection accuracy rate, false judgment rate, and missed judgment rate of the touch signal, and the stability and reliability of the system under different conditions are evaluated. Among them, the performance verification indicators include the detection accuracy rate, false judgment rate, missed judgment rate, and the response time of the system, ensuring that the system can maintain high-performance performance under various touch environments and noise conditions. According to the performance verification results, further optimize the parameters and rules of the system to ensure that the system can quickly adapt to changes in touch force and environmental noise. If performance deficiencies or slow adaptation speeds are found during the verification process, the reasons need to be further analyzed, and the fruit fly algorithm is used again to fine-tune the fuzzy controller until the system performance meets the requirements.

[0094] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claimed rights.

Claims

1. A dynamic threshold adjustment method for ITO touch signals based on fuzzy control, characterized in that It includes the following steps: S1. Collect ITO touch signals and environmental noises and perform preprocessing to obtain effective features, including touch signal intensity, change rate, and environmental noise intensity; S2. Design a fuzzy controller, select touch signal intensity, change rate, and environmental noise intensity as input variables, and fuzzify them into membership functions; S3. According to the dynamic changes of touch signals and environmental noises, formulate a fuzzy rule base and define fuzzy language variables; S4. Through a fuzzy inference mechanism, dynamically adjust the touch signal detection threshold according to the fuzzy values of the input variables, and obtain an accurate touch signal detection threshold through defuzzification; S5. Use the fruit fly algorithm to optimize the membership functions and fuzzy rules of the fuzzy controller to find the optimal threshold adjustment strategy; S6. According to the optimization results of the fuzzy controller and the fruit fly algorithm, update the touch signal detection threshold in real time and verify its performance in ITO touch under different touch environments and noises.

2. The dynamic threshold adjustment method for ITO touch signal based on fuzzy control according to claim 1, characterized in that: The specific content of S1 includes: Collect the original touch signal data through the sensing layer of the ITO touch screen, and use an environmental noise sensor to capture synchronous environmental noise data. After collection, store the touch signal and environmental noise data in different data channels respectively; Perform preprocessing on the collected touch signal and environmental noise data, including filtering and denoising operations, and normalize the touch signal and environmental noise data; Extract effective features from the preprocessed touch signal and environmental noise data, including touch signal intensity, change rate, and environmental noise intensity, and integrate the extracted touch signal intensity, change rate, and environmental noise intensity into a feature vector.

3. A dynamic threshold adjustment method for ITO touch control signals based on fuzzy control according to claim 1, characterized in that: The specific content of S2 includes: Design a fuzzy controller and clarify the input variables of the fuzzifier. Among them, the input variables of the fuzzy controller are touch signal intensity, change rate, and environmental noise intensity. For the three input variables, design corresponding fuzzification strategies, divide the touch signal intensity into three fuzzy sets: weak, medium, and strong, divide the change rate into three fuzzy sets: slow, medium, and fast, and divide the environmental noise intensity into three fuzzy sets: low, medium, and high; According to the characteristics and actual needs of the input variables, construct membership functions for each fuzzy set. For touch signal intensity, use a Gaussian membership function, for change rate, use a triangular membership function, and for environmental noise intensity, select a trapezoidal membership function; Determine the universe of discourse of each input variable, that is, the range of values of the input variable, and divide the universe of discourse into several fuzzy subsets. Each subset corresponds to a fuzzy set, and then set the parameters of the membership function to complete the construction of the membership function.

4. A dynamic threshold adjustment method for ITO touch signals based on fuzzy control according to claim 3, characterized in that: The setting of the universe of discourse of the input variables is as follows: The universe of discourse of each input variable is specifically: the universe of discourse range of touch signal intensity is [0, 10], indicating that the intensity of the touch signal ranges from none to maximum; The universe of discourse range of the change rate is [0, 5], indicating that the change rate of the touch signal ranges from static to fastest; The universe of discourse range of environmental noise intensity is [0, 8], indicating that the environmental noise intensity ranges from none to maximum.

5. A dynamic threshold adjustment method for ITO touch signals based on fuzzy control according to claim 3, characterized in that: The setting of the parameters of the membership function is as follows: For touch signal intensity: The weak touch fuzzy set uses a Gaussian membership function with the center point set at a lower position in the universe of discourse and a narrow width to cover the range of weak touch signal strength. The parameters are: the center point is 2 and the width is 1.

5. The medium touch fuzzy set uses a Gaussian membership function with the center point located at the middle position in the universe of discourse and a moderate width to cover the range of medium touch signal strength. The parameters are: the center point is 5 and the width is 1.

5. The strong touch fuzzy set has the center point of the Gaussian membership function set at a higher position in the universe of discourse and a narrow width to cover the range of strong touch signal strength. The parameters are: the center point is 8 and the width is 1.5; For the rate of change: The slow change fuzzy set uses a triangular membership function with the vertex located at the starting part of the universe of discourse. The left boundary starts from the starting point of the universe of discourse and the right boundary extends to the middle position. The parameters are: the vertex is at 1, the left boundary is 0, and the right boundary is 2. The medium change fuzzy set has the vertex of the triangular membership function located at the middle position in the universe of discourse. The left boundary starts from the right boundary of the slow one and the right boundary extends to the left boundary of the fast one. The parameters are: the vertex is at 3, the left boundary is 2, and the right boundary is 4. The fast change fuzzy set has the vertex of the triangular membership function located at the end part of the universe of discourse. The left boundary starts from the right boundary of the medium one and the right boundary extends to the end point of the universe of discourse. The parameters are: the vertex is at 5, the left boundary is 4, and the right boundary is 6; For the environmental noise intensity: The low noise fuzzy set uses a trapezoidal membership function with the left bottom starting from the starting point of the universe of discourse. The left top and the right top are respectively located at lower positions in the universe of discourse, and the right bottom extends to the middle position. The parameters are: the left bottom is 0, the left top is 2, the right top is 3, and the right bottom is 4. The medium noise fuzzy set has the left bottom and the left top of the trapezoidal membership function respectively located at the middle position in the universe of discourse, and the right top and the right bottom respectively extend to higher positions. The parameters are: the left bottom is 2, the left top is 4, the right top is 6, and the right bottom is 8. The high noise fuzzy set has the left bottom and the left top of the trapezoidal membership function respectively located at higher positions in the universe of discourse, and the right top and the right bottom extend to the end point of the universe of discourse. The parameters are: the left bottom is 5, the left top is 7, the right top is 8, and the right bottom is 10.

6. A method for dynamically adjusting the threshold of ITO touch signals based on fuzzy control according to claim 3, characterized in that: The specific content of S3 includes: Defining the touch signal detection threshold as the output variable and analyzing the relationships between the three input variables of touch signal strength, rate of change, and environmental noise intensity and the output variable; Defining fuzzy linguistic variables according to the fuzzy sets of the input variables. For touch signal strength, the linguistic variables are defined as "weak", "medium", and "strong". For rate of change, the linguistic variables are defined as "slow", "medium", and "fast". For environmental noise intensity, the linguistic variables are defined as "low", "medium", and "high". Each linguistic variable corresponds to a fuzzy set, and its fuzzy characteristics are described by the membership function; Based on the relationships between the input variables and the output variable, further refining the fuzzy rules. For each combination of linguistic variables of touch signal and environmental noise, formulating specific fuzzy rules to describe the output behavior of the system, that is, the adjustment method of the touch signal detection threshold, and integrating the refined fuzzy rules into a fuzzy rule base.

7. A dynamic threshold adjustment method for ITO touch control signals based on fuzzy control according to claim 1, characterized in that: The specific content of S4 includes: In the fuzzy inference mechanism, the parameters and structure of the fuzzy controller are initialized, including determining the universes of discourse of the input variables and output variables, the fuzzy set partitioning, and the membership function types. The actual measured values of the three input variables, i.e., the touch signal strength, the change rate, and the environmental noise strength, are converted into corresponding fuzzy values through the defined membership functions. The fuzzy values of the input variables are input into the fuzzy rule base for fuzzy inference. For each fuzzy rule, its activation degree is calculated according to the membership functions of the input variables. For each rule, the membership values of the input variables are calculated, and the activation weight of the fuzzy rule is determined according to the fuzzy operation. According to the activation weights of all fuzzy rules, the fuzzy value of the output variable is calculated. The fuzzy set of the output variable obtained by fuzzy inference is defuzzified through a defuzzification method, and the fuzzy value of the output variable is converted into an exact value to obtain the touch signal detection threshold.

8. A dynamic threshold adjustment method for ITO touch signals based on fuzzy control according to claim 7, characterized in that: The calculation process of the fuzzy value of the output variable is as follows: For each fuzzy rule, calculate the membership values of the input variables, and take the minimum value of the membership values of the input variables as the activation weight. For each fuzzy rule, calculate the square root of the sum of the squares of the membership values of the input variables to obtain the comprehensive membership value. Calculate the exponential function of the membership values of the input variables, find the average value, and take the natural logarithm after adding 1 to the average value to obtain the logarithmic compression value. Multiply the activation weight of each fuzzy rule by the comprehensive membership value, sum them up and divide by the sum of all activation weights to obtain the preliminary comprehensive fuzzy value, and multiply the preliminary comprehensive fuzzy value by the logarithmic compression value to obtain the fuzzy value of the output variable. The calculation process of the touch signal detection threshold is as follows: Calculate the sum of the membership values of each input variable in all fuzzy rules, and divide it by three times the number of fuzzy rules to obtain an average membership value. Substitute the average membership value into the sine function to obtain a periodic adjustment factor. Combine the calculated fuzzy value of the output variable with the periodic adjustment factor to calculate the final touch signal detection threshold.

9. A dynamic threshold adjustment method for ITO touch control signals based on fuzzy control according to claim 7, characterized in that: The specific steps of S5 include: Set the fruit fly algorithm and initialize the parameters of the fruit fly algorithm, including the population size, the number of iterations, and the search range. At the same time, clarify the parameters to be optimized of the fuzzy controller, i.e., the shape parameters of the membership functions and the weight coefficients in the fuzzy rules. Encode the parameters to be optimized as the position information of the fruit fly individuals. Each fruit fly individual represents a combination of membership functions and fuzzy rules, and then randomly generate the initial fruit fly population. In each iteration process, the fruit fly algorithm calculates the corresponding fitness value according to the position information of the individuals. And the fruit fly individuals search for better positions in the solution space through the olfactory and visual search mechanisms. After each iteration, update the position information of the fruit fly population, retain the individuals with higher fitness, and eliminate the individuals with lower fitness, gradually approaching the optimal solution. After multiple iterations, the fruit fly algorithm converges to the optimal solution, that is, a set of optimal membership function parameters and fuzzy rule weight coefficients are obtained, and then they are applied to the fuzzy controller to form the optimal threshold adjustment strategy.

10. A dynamic threshold adjustment method for ITO touch signals based on fuzzy control according to claim 9, characterized in that: The specific steps of S6 include: Based on the optimization results of the fuzzy controller and the fruit fly algorithm, the touch signal detection threshold is updated in real time. The optimized membership function parameters and fuzzy rule weight coefficients are applied to the fuzzy controller, enabling it to dynamically adjust the touch signal detection threshold according to the real-time measured values of the current touch signal intensity, change rate, and environmental noise intensity; Under different touch environments and noise conditions, the performance of the updated touch signal detection threshold is verified. Multiple experimental scenarios are designed to simulate different touch forces and environmental noise levels. In each experimental scenario, the touch detection results of the system are recorded, including the detection accuracy rate, false judgment rate, and missed judgment rate of the touch signal, to evaluate the stability and reliability of the system under different conditions; According to the performance verification results, the parameters and rules of the system are further optimized. If insufficient performance or slow adaptation speed is found during the verification process, the reasons need to be further analyzed, and the fruit fly algorithm is used again to fine-tune the fuzzy controller until the system performance meets the requirements.

Images