Pressure sensor performance detection method and system

Abstract

The embodiment of the invention relates to the technical field of data analysis, in particular to a pressure sensor performance detection method and system, which is based on a structure of a target multivariate decision tree detection attribute identification branch, can classify and identify various performance detection data, and ensures the accuracy and pertinence of data acquisition. The confidence relation list is determined by means of the target mapping relation network paired with the target recognition unit to obtain the third performance detection response information, the complex relation between the detection information can be fully considered, and the evaluation accuracy is improved. And the second performance detection response information is processed by using the association identification unit to obtain fourth performance detection response information, and comprehensive analysis of different performance data can be realized through multi-unit cooperation. And performance index evaluation data is determined based on the third and fourth performance detection response information, so that a comprehensive, accurate and scientific detection evaluation result can be provided for the performance of the pressure sensor.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and more specifically, to a method and system for detecting the performance of a pressure sensor. Background Art

[0002] In the field of detecting the performance of pressure sensors, traditional detection methods often have many problems. In the face of multi-dimensional sensing performance detection data, traditional detection means lack an effective classification and recognition mechanism and cannot accurately obtain key information from complex data. Moreover, when performing analysis and evaluation, the complex correlation relationships between various pieces of information are not considered, resulting in inaccurate evaluation results. In addition, there is a lack of an analysis method with multi-unit cooperation, and it is impossible to comprehensively analyze various performance aspects of the pressure sensor in depth, thus unable to achieve a comprehensive and scientific performance index evaluation. Summary of the Invention

[0003] In view of this, the present invention provides a method and system for detecting the performance of a pressure sensor.

[0004] An embodiment of the present invention provides a method for detecting the performance of a pressure sensor, which is applied to a pressure sensor performance detection system. The method includes: obtaining first performance detection response information in multi-dimensional sensing performance detection data through a target recognition unit, where the target recognition unit is a detection attribute recognition unit in a detection attribute recognition branch of a target multi-decision tree, and the detection attribute recognition branch includes the target recognition unit and at least one associated recognition unit, and at least one of the associated recognition units is used to process at least one second performance detection response information determined based on the multi-dimensional sensing performance detection data respectively; determining a confidence relationship list paired with the first performance detection response information based on at least one target mapping relationship network paired with the target recognition unit, and determining third performance detection response information based on the first performance detection response information and the confidence relationship list, where the relationship network size of the target mapping relationship network matches the detection response vector size of the first performance detection response information; obtaining at least one fourth performance detection response information obtained by at least one of the associated recognition units processing their respective corresponding second performance detection response information; and determining performance index evaluation data paired with the multi-dimensional sensing performance detection data based on the third performance detection response information and at least one of the fourth performance detection response information.

[0005] The present invention also provides a pressure sensor performance detection system, including: a memory for storing program instructions and data; a processor for being coupled with the memory and executing the instructions in the memory to implement the method as described above.

[0006] The present invention also provides a computer storage medium containing instructions that, when executed on a processor, implement the above method.

[0007] Based on the structure of the attribute recognition branch of the target multi-decision tree, the embodiments of the present invention can classify and identify various performance detection data, ensuring the accuracy and pertinence of data acquisition. By determining the confidence relationship list with the help of the target mapping relationship network paired with the target recognition unit to obtain the third performance detection response information, the complex relationships between various detection information can be fully considered, improving the accuracy of evaluation. Using the association recognition unit to process the second performance detection response information to obtain the fourth performance detection response information, multi-unit cooperation can achieve a comprehensive analysis of different performance data. Based on the third and fourth performance detection response information to determine the performance index evaluation data, it can provide a comprehensive, accurate and scientific detection and evaluation result for the performance of the pressure sensor. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The accompanying drawings herein are incorporated into and constitute a part of this specification, showing embodiments consistent with the present invention and, together with the specification, are used to explain the principles of the present invention.

[0009] Figure 1 It is a schematic flowchart of the steps of a method for detecting the performance of a pressure sensor provided by an embodiment of the present invention.

[0010] Figure 2 It is a block diagram of the structure of a system for detecting the performance of a pressure sensor provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] The technical solutions in the present invention will be described below with reference to the accompanying drawings.

[0012] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention. It should be noted that the terms "first", "second", etc. in the specification and the above accompanying drawings of the present invention are used to distinguish similar objects and do not necessarily need to describe a specific order or sequence.

[0013] The method embodiments provided by the embodiments of the present invention may be executed in a pressure sensor performance detection system, a computer device, or a similar computing device. Taking running on a pressure sensor performance detection system as an example, the pressure sensor performance detection system may include one or more processors (the processors may include, but are not limited to, processing devices such as a microprocessor MCU or a programmable logic device FPGA), and a memory for storing data. Optionally, the above-mentioned pressure sensor performance detection system may further include a transmission device for communication functions. Those of ordinary skill in the art can understand that the above structure is only illustrative and does not limit the structure of the above-mentioned pressure sensor performance detection system. For example, the pressure sensor performance detection system may further include more or fewer components than those shown above, or have a different configuration from that shown above.

[0014] The memory can be used to store computer programs. For example, software programs and modules of application software, such as the computer program corresponding to a pressure sensor performance detection method in the embodiments of the present invention. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, the above-mentioned method is implemented. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memories. In some instances, the memory may further include a memory remotely set relative to the processor, and these remote memories can be connected to the pressure sensor performance detection system through a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and their combinations.

[0015] The transmission device is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wireless network provided by a communication provider of the pressure sensor performance detection system. In one instance, the transmission device includes a network adapter (abbreviated as NIC for Network Interface Controller), which can be connected to other network devices through a base station and thus communicate with the Internet. In one instance, the transmission device may be a radio frequency (abbreviated as RF) module, which is used to communicate with the Internet wirelessly.

[0016] Combined with the above content, please refer to Figure 1 , Figure 1 is a schematic flowchart of a pressure sensor performance detection method provided by the embodiments of the present invention. This method is applied to a pressure sensor performance detection system and may further include step 110 - step 140.

[0017] Step 110: Obtain the first performance detection response information in the multi-dimensional sensing performance detection data through the target recognition unit.

[0018] Among them, the target recognition unit is a detection attribute recognition unit in the detection attribute recognition branch of the target multi - decision tree. The detection attribute recognition branch includes the target recognition unit and at least one associated recognition unit. At least one of the associated recognition units is used to process at least one second performance detection response information determined based on the multi - dimensional sensing performance detection data. Further, the multi - dimensional sensing performance detection data includes static performance detection data, dynamic performance detection data, environmental adaptability detection data, and durability stability detection data for the target pressure sensor.

[0019] Step 120: Based on at least one target mapping relationship network paired with the target recognition unit, determine a confidence relationship list paired with the first performance detection response information, and determine the third performance detection response information based on the first performance detection response information and the confidence relationship list.

[0020] Among them, the relationship network size of the target mapping relationship network matches the detection response vector size of the first performance detection response information.

[0021] Step 130: Obtain at least one fourth performance detection response information obtained by at least one of the associated recognition units processing their respective corresponding second performance detection response information.

[0022] Step 140: Based on the third performance detection response information and at least one of the fourth performance detection response information, determine the performance index evaluation data paired with the multi - dimensional sensing performance detection data.

[0023] It can be understood that the pressure sensor performance detection system, as the execution body of the embodiment of the present invention, is used to implement the above - mentioned steps 110 - step 140 in the entire detection and evaluation process.

[0024] First, in step 110, the target recognition unit starts to obtain the first performance detection response information in the multi-dimensional sensing performance detection data. The multi-dimensional sensing performance detection data in the embodiments of the present invention covers very comprehensive content, including static performance detection data, dynamic performance detection data, environmental adaptability detection data, and durability stability detection data for the target pressure sensor. For example, in terms of static performance detection data, it may include measurement error data in accuracy detection, such as the deviation between the measured value and the true value of a certain pressure sensor under a specific pressure. For example, when the pressure is 100 kPa, the measured value is 100.5 kPa and the true value is 100 kPa, and this deviation data can be part of the accuracy detection; it may also include the discrete situation of the output values when measuring the same pressure multiple times in repeatability detection. For example, when measuring the 50 kPa pressure 10 times repeatedly, there may be a certain fluctuation range for each output value. In the dynamic performance detection data, there will be data related to frequency response detection, such as the amplitude-frequency characteristic data of the pressure sensor for different frequency pressure signals. It may be the change of the output amplitude with frequency in the frequency range of 100 Hz - 1000 Hz. For some sensors, the output amplitude decreases significantly at 500 Hz compared with the low-frequency band; and data such as the rise time and overshoot in step response detection. For example, the rise time of a certain sensor is 2 ms and the overshoot is 15%, etc. The environmental adaptability detection data involves temperature drift data under temperature influence detection, such as in the range of -20°C to +60°C, the zero-point temperature drift is ±0.3 mV / °C, and the sensitivity temperature drift is ±0.05% / °C; humidity influence coefficient data under humidity influence detection. For example, when the humidity changes from 30%RH to 80%RH, the ratio of the change in the sensor output to the full-scale output; and vibration stability data in vibration and shock influence detection. For example, under a sinusoidal vibration of 10 Hz - 1000 Hz and an amplitude of 1 g, the root mean square value of the output fluctuation is 0.5% of the full-scale output, etc. The durability stability detection data includes aging rate data in the aging test. For example, after 1500 hours of aging test, the sensitivity of the sensor changes from 1.2 mV / Pa to 1.18 mV / Pa, and the aging rate is 1.67%, etc. And the target recognition unit is a detection attribute recognition unit in the detection attribute recognition branch of the target multi-decision tree. In addition to the target recognition unit, this detection attribute recognition branch also includes at least one associated recognition unit, and these associated recognition units will respectively process at least one second performance detection response information determined based on the multi-dimensional sensing performance detection data.

[0025] Next, step 120 is entered. Based on at least one target mapping relationship network paired with the target recognition unit, a confidence relationship list paired with the first performance detection response information is determined, and then the third performance detection response information is determined based on the first performance detection response information and the confidence relationship list. In the embodiments of the present invention, the relationship network size of the target mapping relationship network matches the detection response vector size of the first performance detection response information. For example, the detection response vector of the first performance detection response information contains data of 5 dimensions, such as the relative error in accuracy detection, the standard deviation in repeatability detection, the amplitude change of the amplitude-frequency characteristic at a specific frequency in dynamic performance detection, the temperature drift in environmental adaptability detection, and the aging rate in durability and stability detection. Then the target mapping relationship network will also have a corresponding relationship structure to match the data of these 5 dimensions. This target mapping relationship network may be constructed based on a large amount of experimental data and empirical data. For example, when testing various pressure sensors before, data of different brands and models of sensors under various performance detections are collected, these data are sorted and analyzed, and the association rules between the performance detection response information and the performance are found and constructed into this target mapping relationship network. Through this target mapping relationship network, a confidence relationship list corresponding to the first performance detection response information can be obtained. For example, if the relative error in the first performance detection response information is 2%, the confidence relationship list corresponding in the target mapping relationship network may show that at this relative error, the confidence level of the sensor performance being at a medium level is 0.6, the confidence level of being at a good level is 0.3, and the confidence level of being at a poor level is 0.1. Then, based on this confidence relationship list and the first performance detection response information, the third performance detection response information is further determined. This third performance detection response information is more comprehensive and accurate information reflecting the sensor performance after comprehensively considering the first performance detection response information and its corresponding confidence relationship.

[0026] Then, in step 130, at least one fourth performance detection response information obtained by processing the second performance detection response information corresponding to each respective associated recognition unit is acquired. The associated recognition unit in the embodiments of the present invention also processes the second performance detection response information based on multi-dimensional sensing performance detection data. For example, the associated recognition unit may specifically process the step response detection part in the dynamic performance detection data. For example, in the step response detection, data such as the rise time, overshoot, and settling time of multiple pressure sensors are used as the second performance detection response information. The associated recognition unit may analyze and process these data according to a preset algorithm or rule. For instance, for the rise time, the associated recognition unit may compare it with the average rise time of the same type of sensor. If the rise time of a certain sensor is 30% longer than the average rise time, it is marked as a case of slower rise time, and the fourth performance detection response information is generated based on this result. For the overshoot, if the overshoot exceeds the set threshold (such as 20%), the associated recognition unit determines it as a case of excessive overshoot and reflects it in the fourth performance detection response information. Similarly, for the humidity impact detection part in the environmental adaptability detection data, the associated recognition unit may analyze the change trend of the sensor output under different humidities. If the change amount of the sensor output exceeds 10% of the full-scale output when the humidity increases from 40%RH to 70%RH, the situation that the sensor is more sensitive to humidity is recorded in the fourth performance detection response information.

[0027] Finally, in step 140, based on the third performance detection response information and at least one fourth performance detection response information, the performance index evaluation data paired with the multi-dimensional sensing performance detection data is determined. For example, the third performance detection response information includes the preliminary evaluation result of the sensor in terms of comprehensive performance obtained according to the first performance detection response information and the confidence relationship list, which may be that the overall performance is at a medium to upper level. The fourth performance detection response information may include problems such as slower rise time and excessive overshoot in the step response of the dynamic performance of the sensor, as well as the situation that the sensor is more sensitive to humidity in terms of the humidity impact of environmental adaptability. Combining these information, the performance index evaluation data will comprehensively and accurately evaluate the performance of the pressure sensor. For example, the performance index evaluation data may conclude that although the pressure sensor performs well in static performance and some dynamic performance aspects, due to problems in step response and humidity impact, the overall performance can only reach the medium level, and in practical applications, attention needs to be paid to controlling the humidity environment or compensating for the step response, etc. In this way, the entire complete process from multi-dimensional sensing performance detection data to the final performance index evaluation data of the pressure sensor performance detection system is completed, which can provide a comprehensive, scientific, and accurate basis for the performance evaluation of the pressure sensor.

[0028] Look at this process from another perspective. When obtaining the first performance detection response information in step 110, for the linearity part of the static performance detection data, taking a certain pressure sensor as an example, after fitting a straight line to the data obtained by measuring multiple pressure points, the linearity is calculated by the maximum deviation between the actual output-input characteristic curve and the fitted straight line. For example, in the pressure range of 0 - 1000 kPa, the maximum deviation is 5 kPa, and the full-scale output value is 10 V, then the linearity is ±0.5%. This linearity data is obtained by the target recognition unit as part of the first performance detection response information. In step 120, the target mapping relationship network may have corresponding associations for such linearity data. For example, in the relationship network, a linearity within ±0.5% may be associated with a relatively high performance confidence level. It may be shown in the confidence relationship list that at this linearity, the confidence level for good sensor performance is 0.8, medium is 0.2, and poor is 0. The third performance detection response information determined based on such a confidence relationship list and the linearity data will contain a more accurate performance evaluation tendency. In step 130, when the association recognition unit processes the frequency response detection data in the dynamic performance detection data as the second performance detection response information, for example, if the amplitude-frequency characteristic curve of a certain sensor drops rapidly in the frequency range of 1000 Hz - 2000 Hz, the association recognition unit may mark this frequency range as the sensitive frequency region of the sensor and reflect it in the fourth performance detection response information. Finally, in step 140, by synthesizing the performance evaluation tendency regarding linearity in the third performance detection response information and the situation regarding the sensitive frequency region in the fourth performance detection response information, the performance index evaluation data can draw the conclusion that the sensor has good performance in the low-frequency band, but there may be problems in the high-frequency band and attention is needed in specific application scenarios.

[0029] In dealing with environmental adaptability detection data, such as zero-point temperature drift in temperature impact detection. For example, for a certain pressure sensor within the temperature range of -10°C to +40°C, the zero-point temperature drift is ±0.2 mV / °C. In step 110, this zero-point temperature drift data is part of the multi-dimensional sensing performance detection data and may be acquired by the target recognition unit as the first performance detection response information. In step 120, based on this zero-point temperature drift data, the target mapping relationship network may show in the confidence relationship list that the sensor has good performance in terms of temperature stability. For example, the confidence level for good performance is 0.7, for medium is 0.3, and for poor is 0. The corresponding third performance detection response information will take this confidence relationship into account. In step 130, when the association recognition unit processes humidity impact detection data, if it is found that when the humidity of the sensor changes from 20%RH to 60%RH, the humidity impact coefficient is 0.03 (i.e., the ratio of the change in the sensor output to the full-scale output when the humidity changes by a certain value), then the fourth performance detection response information records that the sensor has a certain anti-interference ability to humidity. Finally, in step 140, the performance index evaluation data synthesizes this information to draw the conclusion that the sensor has good performance in terms of temperature adaptability and also has a certain ability in terms of humidity adaptability, but may still need further optimization.

[0030] Regarding the aging rate in the durable stability detection data, for example, after a certain pressure sensor undergoes a 2000-hour aging test, the sensitivity changes from 1.1 mV / Pa to 1.08 mV / Pa, and the aging rate is 1.82%. In step 110, this aging rate data is acquired by the target recognition unit. In step 120, based on the aging rate, the target mapping relationship network shows in the confidence relationship list that the sensor is at a medium level in terms of durable stability. For example, the confidence level for good performance is 0.3, for medium is 0.5, and for poor is 0.2. The third performance detection response information will include this confidence-based evaluation. In step 130, if the association recognition unit has no other association processing specifically for the aging rate (no other special processing situations), then the fourth performance detection response information is mainly the result of the processing by other association recognition units. Finally, in step 140, the performance index evaluation data combines the evaluation of the medium level of durable stability in the third performance detection response information and other results in the fourth performance detection response information to comprehensively obtain the overall performance evaluation of the sensor. For example, the overall performance is at a medium level, and it is necessary to calibrate regularly during long-term use to ensure the measurement accuracy and other conclusions.

[0031] In the step response detection part of the dynamic performance detection data, in addition to the rise time and overshoot mentioned above, the settling time is also an important indicator. For example, the settling time of a certain pressure sensor is 10 ms. In step 110, this settling time data is part of the multi-dimensional sensing performance detection data and is acquired by the target recognition unit. In step 120, based on the settling time data, the target mapping relation network shows in the confidence relation list that the sensor is at a normal level in terms of the settling time of the step response. For example, the confidence level for good performance is 0.5, medium is 0.4, and poor is 0.1. The third performance detection response information takes this confidence level into account. In step 130, when the association recognition unit processes this settling time data and other step response data, it may comprehensively judge the overall performance of the sensor in terms of the step response, which is reflected in the fourth performance detection response information. Finally, in step 140, the performance index evaluation data synthesizes the third performance detection response information and the fourth performance detection response information, and concludes that although the settling time of the sensor in terms of the step response is normal, due to problems with the rise time or overshoot, the overall step response performance needs to be improved.

[0032] Throughout the process, the pressure sensor performance detection system detects and evaluates the performance of the pressure sensor from a multi-dimensional perspective through the coordinated work of each unit and link, making the evaluation results comprehensive and accurate.

[0033] Furthermore, the first performance detection response information is acquired by the target recognition unit from the multi-dimensional sensing performance detection data. The multi-dimensional sensing performance detection data covers the static performance detection data of the pressure sensor (such as data on accuracy, repeatability, resolution, etc.), dynamic performance detection data (such as data related to frequency response, step response), environmental adaptability detection data (data on temperature, humidity, vibration, and shock effects), and durability and stability detection data (such as data from aging tests). The first performance detection response information is obtained by screening a part of the multi-dimensional sensing performance detection data by the target recognition unit. For example, the target recognition unit may extract the value of the measurement error at a certain specific pressure from the accuracy detection data, or select the amplitude-frequency characteristic value at a certain frequency from the dynamic performance detection data. These values are the basis for subsequent analysis and processing.

[0034] The second performance detection response information is determined based on multi-dimensional sensing performance detection data and is processed separately by at least one associated recognition unit. These associated recognition units and the target recognition unit are in the same detection attribute recognition branch. Similar to the first performance detection response information, the second performance detection response information is also part of the multi-dimensional sensing performance detection data, but is processed by the associated recognition unit. For example, the associated recognition unit may focus on the step response part of the dynamic performance detection data, such as data like rise time, overshoot, and settling time as the second performance detection response information, or for the humidity impact detection part of the environmental adaptability detection data, such as the change amount of the sensor output when the humidity changes, etc. as the second performance detection response information.

[0035] The third performance detection response information is determined based on the first performance detection response information and the paired confidence relationship list. First, the confidence relationship list paired with the first performance detection response information is determined according to the target mapping relationship network paired with the target recognition unit, and then the third performance detection response information is obtained by integrating the first performance detection response information and the confidence relationship list. The third performance detection response information is the result after considering the confidence relationship on the basis of the first performance detection response information. For example, if a certain index in the first performance detection response information shows the performance value of the sensor in a certain aspect, through the confidence levels corresponding to different performance levels (such as good, medium, poor) of this value in the confidence relationship list, a more comprehensive result that can better reflect the performance of the sensor is obtained through integration. This result contains more performance evaluation tendency information.

[0036] The fourth performance detection response information is obtained by at least one associated recognition unit processing the corresponding second performance detection response information. The fourth performance detection response information is the result of the associated recognition unit performing specific processing on the second performance detection response information. For example, the associated recognition unit analyzes and processes the amplitude-frequency characteristics and phase-frequency characteristics of the sensor at different frequencies for the frequency response detection part of the dynamic performance detection data, and obtains information such as the overall performance evaluation of the sensor in terms of frequency response. These information constitute the fourth performance detection response information.

[0037] In some possible examples, the target multi-decision tree is a decision-making structure used to analyze and make decisions on the performance detection data of a pressure sensor. It contains multiple branches and nodes, and processes the input data through different paths and judgment rules to obtain the evaluation result of the performance of the pressure sensor. In the embodiment of the present invention, it provides a framework for the analysis of the performance detection data of the pressure sensor. For example, different branches can correspond to different types of performance detection data (static performance, dynamic performance, etc.), and the nodes can represent different judgment conditions or data processing steps, so that the performance evaluation result can be gradually obtained according to the multi-dimensional sensing performance detection data of the pressure sensor.

[0038] The detection attribute recognition branch is a component of the target multi - decision tree, which includes a detection attribute recognition unit and a correlation recognition unit. This branch is mainly responsible for identifying and processing specific attributes in the performance detection data of the pressure sensor. It classifies and processes the performance detection data of the pressure sensor according to different attributes. For example, a detection attribute recognition branch may specifically process the dynamic performance detection data, and the detection attribute recognition unit and the correlation recognition unit in it respectively identify, analyze and process different parts of the dynamic performance detection data, thus helping to more carefully and specifically evaluate the performance of the pressure sensor in terms of dynamic performance.

[0039] The detection attribute recognition unit is a unit in the detection attribute recognition branch. In the embodiment of the present invention, the target recognition unit can be a detection attribute recognition unit. Its main function is to obtain specific performance detection response information from the multi - dimensional sensing performance detection data. The detection attribute recognition unit is responsible for the preliminary screening and extraction of the multi - dimensional sensing performance detection data. For example, when processing the static performance detection data, the detection attribute recognition unit can accurately extract the meaningful parts for subsequent analysis from the data in multiple aspects such as accuracy detection and repeatability detection. For example, it can extract the measurement error value from the accuracy detection data, etc., providing basic data for subsequent analysis and processing.

[0040] The target mapping relationship network is a data relationship structure, and its network size matches the size of the detection response vector of the first performance detection response information. It stores the mapping relationship between the first performance detection response information and the performance evaluation, and this relationship is constructed based on a large amount of experimental data, empirical data or preset rules. The target mapping relationship network is used to determine the confidence relationship list paired with the first performance detection response information. For example, when the first performance detection response information includes the relative error value in the accuracy detection of a certain pressure sensor, the target mapping relationship network can determine the confidence relationship list of the sensor performance at different levels (such as good, medium, poor) under this relative error value according to the pre - stored relationship between the relative error value and the performance evaluation.

[0041] The confidence relationship list is paired with the first performance detection response information, and it lists the confidence values of the sensor performance at different levels (such as good, medium, poor, etc.) based on the first performance detection response information. These confidence values are determined based on the target mapping relationship network. The confidence relationship list provides a basis for determining the third performance detection response information. By combining the confidence values in the confidence relationship list with the actual data in the first performance detection response information, the performance of the pressure sensor can be evaluated more comprehensively and accurately, and the third performance detection response information including the performance evaluation tendency can be obtained.

[0042] Based on the above content, an exemplary introduction to different performance detection response information and performance index evaluation data is as follows.

[0043] I. Feature Vector Form of the First Performance Detection Response Information Vector Constituent Elements 1) Elements related to static performance; For example, taking a pressure sensor as an example, in terms of accuracy, if the measurement error is 3%, this value can be used as an element in the feature vector. In terms of repeatability, for example, the standard deviation of the output values of measuring a certain pressure value 10 times is 0.5 units (this unit depends on the specific physical quantity output by the sensor, such as millivolts for voltage values), and this value can also be used as an element. Additionally, if the resolution is 0.05 units (such as the pressure unit being Pascal), it can also be included in the vector.

[0044] 2) Elements related to dynamic performance; For frequency response, the amplitude-frequency characteristic values at specific frequencies, such as the amplitude-frequency characteristic value being 0.8 at 100 Hz (for example, a value normalized with respect to the amplitude in the low-frequency band), and the phase-frequency characteristic values (for example, the phase shift being 10 degrees at 100 Hz, which can be converted into a suitable numerical form and included in the vector). For step response, values such as the rise time being 2 ms, the overshoot being 15%, and the settling time being 10 ms can all be used as elements in the feature vector.

[0045] 3) Elements related to environmental adaptability; In terms of temperature influence, for example, the zero-point temperature drift is ±0.3 mV / °C, and the sensitivity temperature drift is ±0.05% / °C, and these values can become vector elements. For humidity influence, if the humidity influence coefficient is 0.03 (the ratio of the change in sensor output to the full-scale output) when the humidity changes from 30%RH to 80%RH, it can be put into the vector. In terms of vibration and shock influence, for example, under a sinusoidal vibration of 10 Hz - 1000 Hz and an amplitude of 1 g, the root mean square value of the output fluctuation ratio to the full-scale output is 0.5%, and this value can be used as a vector element.

[0046] 4) Elements related to durability and stability; For example, after a 1500-hour aging test, the sensor sensitivity changes from 1.2 mV / Pa to 1.18 mV / Pa, and the aging rate is 1.67%, and this aging rate value can be used as an element in the feature vector.

[0047] For example, the eigenvector of the first performance detection response information of a pressure sensor is [3%, 0.5, 0.05, 0.8, 10, 2, 15%, 10, ±0.3, ±0.05%, 0.03, 0.5%, 1.67%]. The element order in the embodiments of the present invention respectively corresponds to the above-mentioned values of accuracy measurement error, repeatability standard deviation, resolution, 100Hz amplitude-frequency characteristic, 100Hz phase-frequency characteristic, rise time, overshoot, settling time, zero-point temperature drift, sensitivity temperature drift, humidity influence coefficient, vibration output fluctuation ratio, aging rate, etc.

[0048] II. Eigenvector form of the second performance detection response information Vector constituent elements: Elements of the processing results of different correlation recognition units; For example, if a correlation recognition unit is dedicated to processing the frequency response part in dynamic performance, the amplitude-frequency characteristic and phase-frequency characteristic values for multiple frequency points can be used as elements. For example, the amplitude-frequency characteristic values at 200Hz, 500Hz, and 1000Hz are 0.7, 0.6, and 0.5 respectively, and the phase-frequency characteristic values are 15 degrees, 20 degrees, and 30 degrees (converted to appropriate numerical forms). These values can form vector elements.

[0049] Another correlation recognition unit processes the humidity influence part in environmental adaptability. The change in the sensor output when the humidity changes in different intervals can be used as an element. For example, when the humidity ranges from 40%RH - 50%RH, 50%RH - 60%RH, and 60%RH - 70%RH, the ratios of the change in the sensor output to the full-scale output are 0.02, 0.03, and 0.04 respectively. These values can become vector elements.

[0050] For example, for the case where one correlation recognition unit processes frequency response and another processes humidity influence, the eigenvector of the second performance detection response information may be [0.7, 15, 0.6, 20, 0.5, 30, 0.02, 0.03, 0.04]. The element order in the embodiments of the present invention respectively corresponds to the values of 200Hz amplitude-frequency characteristic, 200Hz phase-frequency characteristic, 500Hz amplitude-frequency characteristic, 500Hz phase-frequency characteristic, 1000Hz amplitude-frequency characteristic, 1000Hz phase-frequency characteristic, 40 - 50%RH humidity influence coefficient, 50 - 60%RH humidity influence coefficient, 60 - 70%RH humidity influence coefficient, etc.

[0051] III. Eigenvector form of the third performance detection response information Vector constituent elements: Comprehensive performance elements based on confidence relationships; The third performance detection response information is obtained based on the first performance detection response information and the confidence relationship list. For example, after comprehensively considering the numerical values in aspects such as accuracy, dynamic performance, environmental adaptability, and durability stability in the first performance detection response information and the corresponding confidence relationships, quantitative values regarding the overall performance at different levels (such as good, medium, poor) are obtained. For example, the confidence for good overall performance is 0.6, for medium is 0.3, and for poor is 0.1, and these values can be used as vector elements.

[0052] Meanwhile, it may also include the weighted comprehensive result of the key performance indicators in the first performance detection response information. For example, a comprehensive value calculated according to certain weights (such as the accuracy weight is 0.3, the dynamic performance weight is 0.3, the environmental adaptability weight is 0.2, and the durability stability weight is 0.2), such as 0.7 (this value is a value reflecting the comprehensive performance tendency obtained according to specific weighted calculation rules), can also be used as a vector element.

[0053] For example, the feature vector of the third performance detection response information is [0.6, 0.3, 0.1, 0.7]. In the embodiments of the present invention, the element order corresponds to the confidence values for good, medium, and poor overall performance and the comprehensive performance tendency value respectively.

[0054] IV. Feature Vector Form of the Fourth Performance Detection Response Information Vector constituent elements: Comprehensive elements of the processing results of the association recognition unit; For example, a quantitative value obtained by comprehensively considering factors such as rise time, overshoot, and settling time from the result of the association recognition unit processing the step response part in dynamic performance. For example, according to a pre-set rule, a value of 0.8 is obtained by comprehensively calculating the rise time of 2 ms, overshoot of 15%, and settling time of 10 ms (this value represents the comprehensive performance in terms of step response, and the calculation rule can be determined based on experience or experiments), and this value can be used as a vector element.

[0055] Regarding the association recognition unit processing the vibration impact part in environmental adaptability, a value obtained by comprehensively considering the output stability of the sensor under different vibration frequencies and amplitudes. For example, in the range of 10 Hz - 100 Hz and amplitude of 0.5 g - 1 g, a value of 0.6 calculated based on the sensor output fluctuation (representing the comprehensive performance under this vibration condition) can be used as a vector element.

[0056] For example, the feature vector of the fourth performance detection response information is [0.8, 0.6]. In the embodiments of the present invention, the element order corresponds to the step response comprehensive performance value and the vibration impact comprehensive performance value respectively.

[0057] V. Eigenvector Form of Performance Index Evaluation Data Elements of the vector: elements of the comprehensive evaluation result; The performance index evaluation data is obtained based on the third performance detection response information and the fourth performance detection response information. For example, by comprehensively considering the overall performance confidence value and the comprehensive performance tendency value in the third performance detection response information, and the comprehensive performance values after processing by each associated recognition unit in the fourth performance detection response information, the numerical value of the final performance evaluation of the pressure sensor is obtained. For example, the probabilities of the final performance evaluation being excellent, good, medium, poor, and very poor are 0.2, 0.3, 0.3, 0.1, and 0.1 respectively, and these numerical values can be used as vector elements.

[0058] At the same time, it may also include some suggestions given according to the performance evaluation result or the quantified numerical values of the indicators. For example, if the evaluation result is medium, a quantified improvement suggestion numerical value is given for the aspects that need to be improved. For example, in terms of dynamic performance improvement, the suggested improvement amount is 0.2 (this numerical value represents the degree of improvement required in dynamic performance and is obtained according to specific evaluation rules), and this numerical value can also be used as a vector element.

[0059] For example, the eigenvector of the performance index evaluation data is [0.2, 0.3, 0.3, 0.1, 0.1, 0.2]. In the embodiments of the present invention, the element order corresponds to the probability numerical values of excellent, good, medium, poor, and very poor and the numerical value of the dynamic performance improvement suggestion respectively.

[0060] In a preferred embodiment, determining the confidence relationship list paired with the first performance detection response information based on at least one target mapping relationship network paired with the target recognition unit, and determining the third performance detection response information based on the first performance detection response information and the confidence relationship list includes: determining the detection element mapping relationship network, the evaluation mapping relationship network, and the performance correction mapping relationship network included in at least one of the target mapping relationship networks, wherein the relationship network sizes of the detection element mapping relationship network, the evaluation mapping relationship network, and the performance correction mapping relationship network match the detection response vector size of the first performance detection response information; determining the response element mapping knowledge set based on the first performance detection response information and the detection element mapping relationship network, and determining the response evaluation mapping knowledge set based on the first performance detection response information and the evaluation mapping relationship network; determining the confidence relationship list paired with the first performance detection response information according to the response element mapping knowledge set and the response evaluation mapping knowledge set; determining the response correction mapping knowledge set based on the first performance detection response information and the performance correction mapping relationship network, and determining the third performance detection response information according to the confidence relationship list and the response correction mapping knowledge set.

[0061] In this embodiment, for the process of determining the confidence relationship list paired with the first performance detection response information based on at least one target mapping relationship network paired with the target recognition unit, and then determining the third performance detection response information, first, determine the detection element mapping relationship network, the evaluation mapping relationship network, and the performance correction mapping relationship network included in at least one target mapping relationship network. The relationship network sizes of these relationship networks match the detection response vector size of the first performance detection response information. Taking the first performance detection response information feature vector mentioned above as an example, for example, the first performance detection response information feature vector is [3%, 0.5, 0.05, 0.8, 10, 2, 15%, 10, ±0.3, ±0.05%, 0.03, 0.5%, 1.67%], and the dimension of this vector determines that the structural dimensions of the detection element mapping relationship network, the evaluation mapping relationship network, and the performance correction mapping relationship network match it.

[0062] Based on the first performance detection response information and the detection element mapping relationship network, determine the response element mapping knowledge set. The detection element mapping relationship network stores the mapping relationships between each element in the first performance detection response information (such as elements like accuracy, repeatability, resolution, etc. at different values) and other relevant knowledge (such as the mapping relationships between these elements and the internal structure and working principle of the sensor, etc.). For each element in the first performance detection response information feature vector, such as the element with a measurement error of 3%, in the detection element mapping relationship network, it may correspond to some knowledge about the error source and influence range in the sensor measurement principle, and the combination of this knowledge forms the response element mapping knowledge set.

[0063] At the same time, based on the first performance detection response information and the evaluation mapping relationship network, determine the response evaluation mapping knowledge set. The evaluation mapping relationship network contains the mapping relationships between different numerical values of the first performance detection response information elements and the evaluation criteria. For example, for the element with a rise time of 2 ms in the first performance detection response information feature vector, in the evaluation mapping relationship network, it may correspond to the evaluation levels of the rise time in the same type of sensor (such as fast, normal, slow, etc.) and other relevant evaluation knowledge corresponding to these levels, and the combination of this relevant knowledge constitutes the response evaluation mapping knowledge set.

[0064] Determine the confidence relationship list paired with the first performance detection response information based on the response element mapping knowledge set and the response evaluation mapping knowledge set. Since the response element mapping knowledge set contains the principled knowledge behind each element of the first performance detection response information, and the response evaluation mapping knowledge set contains the evaluation-related knowledge, the combination of the two can accurately determine the confidence relationship list. For example, according to the knowledge about the source and influence range of measurement errors in the response element mapping knowledge set, and the knowledge about the evaluation level of measurement errors in the same type of sensors in the response evaluation mapping knowledge set, when the measurement error is 3%, the confidence values of the sensor performance at different levels (such as good, medium, poor) can be determined. For example, the confidence for good is 0.3, the confidence for medium is 0.5, and the confidence for poor is 0.2. These values constitute the confidence relationship list.

[0065] Based on the first performance detection response information and the performance correction mapping relationship network, determine the response correction mapping knowledge set. The performance correction mapping relationship network stores the mapping relationship between the numerical values of each element of the first performance detection response information and the possible correction measures or compensation knowledge. For example, for the element of the sensitivity temperature drift of ±0.05% / °C in the feature vector of the first performance detection response information, in the performance correction mapping relationship network, it may correspond to some technical means for compensating for temperature drift or knowledge on how to correct this influence in subsequent calculations. These knowledge constitute the response correction mapping knowledge set.

[0066] Finally, determine the third performance detection response information based on the confidence relationship list and the response correction mapping knowledge set. The third performance detection response information is not only based on the preliminary judgment of the sensor performance level in the confidence relationship list, but also combines the knowledge in the response correction mapping knowledge set about how to correct or compensate for the performance. For example, on the basis that the confidence relationship list shows that the sensor performance is at a medium level (such as the confidence for good is 0.3, the confidence for medium is 0.5, and the confidence for poor is 0.2), combined with the knowledge in the response correction mapping knowledge set about correcting the influence of measurement errors, temperature drift, etc., a more comprehensive third performance detection response information is obtained. This information may include the performance adjustment tendency after considering the correction measures, such as the degree to which the performance approaches the good level after correction.

[0067] Thus, by dividing the target mapping relationship network into a detection element mapping relationship network, an evaluation mapping relationship network, and a performance correction mapping relationship network in detail, the first performance detection response information can be analyzed and processed more meticulously and comprehensively. Determining the response element mapping knowledge set and the response evaluation mapping knowledge set to accurately construct the confidence relationship list makes the judgment of the sensor performance at different levels more scientific and reasonable. Further determining the response correction mapping knowledge set to obtain the third performance detection response information can not only accurately evaluate the current performance of the sensor, but also take into account the factors of performance correction, providing more guiding information for subsequent improvement of the sensor performance or optimization of the sensor use. This technical solution helps to improve the accuracy and comprehensiveness of the performance detection and evaluation of the pressure sensor, providing reliable technical support for the performance optimization, quality control, and reasonable use of the pressure sensor in different application scenarios.

[0068] In an alternative embodiment 1, before obtaining at least one fourth performance detection response information processed by at least one of the associated recognition units from their respective corresponding second performance detection response information, it further includes: obtaining the u-th second performance detection response information in the multi-dimensional sensing performance detection data through the u-th associated recognition unit, where u is an integer not less than 1 and not greater than X, and X is the number of associated recognition units included in the detection attribute recognition branch; determining a confidence relationship list paired with the u-th second performance detection response information based on at least one associated mapping relationship network paired with the u-th associated recognition unit, and determining the u-th fourth performance detection response information based on the u-th second performance detection response information and the confidence relationship list.

[0069] In this replaceable Embodiment 1, before obtaining at least one fourth performance detection response information processed by at least one associated recognition unit from their respective corresponding second performance detection response information, taking the above-mentioned multi-dimensional sensing performance detection data as an example, which contains a lot of data in many aspects, and these data constitute the source of the second performance detection response information. First, the u-th associated recognition unit obtains the u-th second performance detection response information from the multi-dimensional sensing performance detection data. In the embodiments of the present invention, u is an integer, and its range is not less than 1 and not greater than X, where X is the number of associated recognition units included in the detection attribute recognition branch. For example, if X = 3, when u = 1, the first associated recognition unit obtains its corresponding second performance detection response information from the multi-dimensional sensing performance detection data. The content of this information is similar to the first performance detection response information described before, and it is also composed of various performance detection-related data. For example, if the associated recognition unit focuses on the step response part in the dynamic performance detection data, the second performance detection response information it obtains may include values such as rise time, overshoot, and settling time. For example, the rise time is 3 ms, the overshoot is 10%, and the settling time is 8 ms, etc. These values constitute a part of the second performance detection response information.

[0070] Next, based on at least one associated mapping relation network paired with the u-th associated recognition unit, a confidence relationship list paired with the u-th second performance detection response information is determined. The function of the associated mapping relation network is similar to the target mapping relation network mentioned before, and its structure is related to the u-th second performance detection response information. For example, for the second performance detection response information containing values such as rise time, overshoot, and settling time, the associated mapping relation network stores the relationship between these values and performance evaluation. Taking the rise time as an example, in the associated mapping relation network, different rise time value ranges correspond to different performance level confidence levels. For example, a rise time in the range of 0 - 2 ms may correspond to a confidence level of 0.8 for good performance, and a rise time in the range of 2 - 5 ms may correspond to a confidence level of 0.6 for medium performance, etc. There are similar corresponding relationships for overshoot and settling time. For example, an overshoot in the range of 0 - 5% may correspond to a confidence level of 0.9 for good performance, and a settling time in the range of 0 - 5 ms may correspond to a confidence level of 0.7 for good performance, etc. Combining this information, a confidence relationship list paired with the u-th second performance detection response information can be determined.

[0071] Then, determine the u-th fourth performance detection response information based on the u-th second performance detection response information and the confidence relationship list. For example, for the second performance detection response information with a rise time of 3 ms, an overshoot of 10%, and a settling time of 8 ms mentioned above, combine the values in the confidence relationship list. Since the rise time is 3 ms, according to the confidence relationship in the association mapping relationship network, the confidence level of medium performance is relatively high. The overshoot of 10% is also in the range with a relatively high confidence level of medium performance, and the same is true for the settling time of 8 ms. Considering these situations comprehensively, determine the u-th fourth performance detection response information. This fourth performance detection response information is a comprehensive evaluation result of the second performance detection response information after considering the confidence relationship. It not only includes the original performance values but also includes the evaluation tendency of these performance values based on the confidence relationship.

[0072] In this way, by separately obtaining the second performance detection response information for each association recognition unit and determining the confidence relationship list based on the paired association mapping relationship network, and then determining the fourth performance detection response information, the processing of the second performance detection response information becomes more meticulous and accurate. This method fully considers the particularity of the performance detection part concerned by each association recognition unit, improving the accuracy of the performance evaluation of each part. For example, when processing the step response part in dynamic performance detection data, it can be accurately evaluated according to its own characteristics. At the same time, through the application of the association mapping relationship network and the confidence relationship list, the determination of the fourth performance detection response information is more scientific and reasonable. It not only includes the information of the original performance values but also incorporates the judgment tendency of the performance level, providing a more reliable basis for comprehensively and accurately evaluating the performance of the pressure sensor finally.

[0073] In another alternative embodiment 2, determining the performance index evaluation data paired with the multi-dimensional sensing performance detection data based on the third performance detection response information and at least one of the fourth performance detection response information includes: combining the third performance detection response vector set for characterizing the third performance detection response information and at least one fourth performance detection response vector set for respectively characterizing at least one of the fourth performance detection response information to obtain a linkage performance detection response vector set; using the linkage performance detection response vector set and the attribute mapping relationship network paired with the detection attribute recognition branch to determine the index evaluation view label set for characterizing the performance index evaluation data.

[0074] In this alternative Embodiment 2, for the process of determining the performance metric evaluation data paired with the multi-dimensional sensing performance detection data based on the third performance detection response information and at least one fourth performance detection response information, this process first involves combining the third performance detection response vector set used to characterize the third performance detection response information and at least one fourth performance detection response vector set used to characterize at least one fourth performance detection response information respectively to obtain a linked performance detection response vector set. Taking the characteristic vector values mentioned before as an example, for instance, the values included in the third performance detection response vector set are [0.6, 0.3, 0.1, 0.7], and these values respectively correspond to the confidence values of the overall performance at different levels (such as good, medium, poor) and the comprehensive performance tendency value. For the fourth performance detection response vector set, for example, one of the fourth performance detection response vectors is [0.8, 0.6], and the element order in the embodiments of the present invention respectively corresponds to the step response comprehensive performance value and the vibration influence comprehensive performance value. Combining such a third performance detection response vector set and at least one fourth performance detection response vector set forms a linked performance detection response vector set. For example, if there is only one fourth performance detection response vector set, then the linked performance detection response vector set may be [0.6, 0.3, 0.1, 0.7, 0.8, 0.6], and this vector set integrates the relevant values of the third performance detection response information and the fourth performance detection response information, and includes the results of evaluating the performance of the pressure sensor from different perspectives.

[0075] Next, using the linked performance detection response vector set and the attribute mapping relationship network paired with the detection attribute recognition branch, determine the index evaluation view label set used to characterize the performance metric evaluation data. The attribute mapping relationship network stores the mapping relationship between each value in the linked performance detection response vector set and the performance metric evaluation. For example, for the value 0.6 in the linked performance detection response vector set (such as the confidence value of the overall performance being good in the third performance detection response vector set), in the attribute mapping relationship network, it may correspond to an evaluation view label regarding the comprehensive evaluation of the sensor performance in terms of accuracy, stability, etc., such as "The overall performance is close to the good level and has advantages in some aspects". For the value 0.8 in the vector set (such as the step response comprehensive performance value in the fourth performance detection response vector set), in the attribute mapping relationship network, it may correspond to an evaluation view label such as "The step response performance is good but there is still room for improvement". Through this mapping analysis of each value in the linked performance detection response vector set, finally determine the index evaluation view label set. This index evaluation view label set is a comprehensive and qualitative evaluation result of the performance of the pressure sensor, which describes the performance of the pressure sensor as a whole and comprehensively considers various factors in the third performance detection response information and the fourth performance detection response information.

[0076] Thus, by combining the third performance detection response vector set and the fourth performance detection response vector set into a linkage performance detection response vector set, the integration of performance detection information from different sources is achieved. This integration method gathers all the numerical information related to performance evaluation together, avoiding the dispersion of information. Then, the index evaluation view label set is determined using the attribute mapping relationship network, and the integrated numerical information is transformed into qualitative evaluation view labels, providing users with an intuitive and comprehensive performance evaluation result. For example, in practical applications, technicians can directly understand the performance status of the pressure sensor in various aspects from the index evaluation view label set, such as the overall performance level, the situation of specific performance (such as step response), etc., which helps to quickly judge whether the pressure sensor meets the requirements and whether further improvement is needed, improving the comprehensiveness and practicality of the performance evaluation of the pressure sensor.

[0077] In yet another alternative embodiment 3, determining at least one of the detection element mapping relationship network, the evaluation mapping relationship network, and the performance correction mapping relationship network included in the target mapping relationship network includes at least one of the following: obtaining a first local detection element relationship network and a second local detection element relationship network, and determining the detection element mapping relationship network based on the operation result of the first relationship feature between the first local detection element relationship network and the second local detection element relationship network; obtaining a first local evaluation relationship network and a second local evaluation relationship network, and determining the evaluation mapping relationship network based on the operation result of the second relationship feature between the first local evaluation relationship network and the second local evaluation relationship network; obtaining a first local performance correction relationship network and a second local performance correction relationship network, and determining the performance correction mapping relationship network based on the operation result of the third relationship feature between the first local performance correction relationship network and the second local performance correction relationship network.

[0078] Further, after determining the performance index evaluation data paired with the multi-dimensional sensing performance detection data based on the third performance detection response information and at least one of the fourth performance detection response information, the following steps are included: Based on the detection attribute recognition branch being the bidirectional long short-term memory branch in the target multi-way decision tree, processing the performance index evaluation data by means of the linear transformation branch connected to the bidirectional long short-term memory branch to obtain performance detection linear quantization data; determining a target fusion feature set based on the first local fusion feature set and the second local fusion feature set paired with the detection feature fusion branch; processing the performance detection linear quantization data based on the target fusion feature set to obtain target performance detection data; based on the target performance detection data, determining a detection attribute recognition result on the basis that the bidirectional long short-term memory branch is the last bidirectional long short-term memory branch in the target multi-way decision tree; and on the basis that the bidirectional long short-term memory branch is not the last bidirectional long short-term memory branch in the target multi-way decision tree, inputting the target performance detection data into the next bidirectional long short-term memory branch.

[0079] In yet another alternative embodiment 3, the technical solution focuses on the determination of each relationship network (detection element mapping relationship network, evaluation mapping relationship network, and performance correction mapping relationship network) in the target mapping relationship network and the subsequent processing based on the performance index evaluation data.

[0080] Regarding the determination of the detection element mapping relationship network, it involves obtaining the first local detection element relationship network and the second local detection element relationship network and determining based on the first relationship feature operation result between them. For example, the first local detection element relationship network may include the relationships between some elements in the static performance detection data of the pressure sensor and other relevant factors, such as the relationship between the measurement error in accuracy detection and certain circuit parameters inside the sensor; the second local detection element relationship network may include the relationships between some elements in the dynamic performance detection data and other relevant factors, such as the relationship between the amplitude-frequency characteristic in frequency response and the structural characteristics of the sensor. The first relationship feature operation result is an operation integration between these two local relationship networks, and this operation may be based on a certain logical relationship or data association rule. Through this operation result, the detection element mapping relationship network can be determined, which comprehensively maps and associates different performance detection elements of the pressure sensor with other relevant knowledge.

[0081] When determining the evaluation mapping relationship network, obtain the first local evaluation relationship network and the second local evaluation relationship network, and then determine based on the operation result of the second relationship feature between them. The first local evaluation relationship network may include the relationship between the evaluation criteria for some performance indicators (such as the step response index in dynamic performance) under specific conditions and other factors (such as the average level of sensors of the same type); the second local evaluation relationship network may include the relationship between the evaluation criteria for some indicators in the environmental adaptability detection data (such as the zero temperature drift under the influence of temperature) and other relevant factors (such as the requirements of the application scenario for temperature stability). The operation result of the second relationship feature integrates these two local evaluation relationship networks, thereby determining the evaluation mapping relationship network, which comprehensively defines the mapping relationship between different performance detection data and evaluation criteria.

[0082] In determining the performance correction mapping relationship network, obtain the first local performance correction relationship network and the second local performance correction relationship network, and determine based on the operation result of the third relationship feature. The first local performance correction relationship network may include the relationship between the preliminary correction strategy for some performance indicators (such as the aging rate in durability stability) and other characteristics of the sensor (such as material characteristics); the second local performance correction relationship network may include the relationship between the correction strategy for some parameters in dynamic performance (such as the phase-frequency characteristic in frequency response) and other relevant factors (such as signal processing methods). The operation result of the third relationship feature integrates these two local performance correction relationship networks, thereby determining the performance correction mapping relationship network, which clarifies the mapping relationship between different performance detection data and performance correction strategies.

[0083] Furthermore, after determining the performance index evaluation data paired with the multi-dimensional sensing performance detection data based on the third performance detection response information and at least one fourth performance detection response information, there are a series of processing steps. When the detection attribute recognition branch is the bidirectional long short-term memory branch in the target multi-way decision tree, the performance index evaluation data is processed based on the linear transformation branch connected to the bidirectional long short-term memory branch to obtain the performance detection linear quantization data. For example, the performance index evaluation data may exist in the form of a qualitative evaluation label set, such as {"overall performance is good, step response needs to be optimized"}, and the linear transformation branch may convert these qualitative data into quantifiable data, such as corresponding the overall performance being good to the value 0.8 (quantifying the degree of excellent performance), and the step response needing to be optimized corresponding to the value 0.3 (quantifying the degree of improvement required), etc., thereby obtaining the performance detection linear quantization data.

[0084] Next, based on the first local fusion feature set and the second local fusion feature set paired with the detection feature fusion branch, a target fusion feature set is determined. The first local fusion feature set may contain features extracted from part of the performance detection data, such as the feature vector [0.8, 10] extracted from the frequency response part of the dynamic performance detection data (here 0.8 is the amplitude-frequency characteristic at a certain frequency, and 10 is the phase-frequency characteristic); the second local fusion feature set may contain features extracted from the environmental adaptability detection data, such as [±0.3, 0.03] (here ±0.3 is the zero-point temperature drift, and 0.03 is the humidity influence coefficient). The target fusion feature set is determined through specific fusion rules (such as weighted average, feature splicing, etc.).

[0085] Then, based on the target fusion feature set, the performance detection linear quantization data is processed to obtain the target performance detection data. For example, the target fusion feature set may adjust or supplement each value in the performance detection linear quantization data, and correct the overall performance quantization value 0.8 in the performance detection linear quantization data according to the relevant features in the target fusion feature set to obtain more accurate target performance detection data.

[0086] When the bidirectional long short-term memory branch is the last bidirectional long short-term memory branch in the target multi-way decision tree, the detection attribute recognition result is determined based on the target performance detection data. This detection attribute recognition result is the final recognition conclusion of the pressure sensor performance. For example, it may be "The pressure sensor reaches an excellent level in all detected performance aspects and can be applied to high-precision measurement scenarios". When the bidirectional long short-term memory branch is not the last bidirectional long short-term memory branch in the target multi-way decision tree, the target performance detection data is input into the next bidirectional long short-term memory branch for further analysis and processing.

[0087] It can be seen that by determining through the combination operation of local relational networks for each relational network in the target mapping relational network, the relational network can be constructed more flexibly and meticulously, improving the accuracy and comprehensiveness of the relational network, thereby enhancing the processing effect of the first performance detection response information. In the subsequent processing based on the performance index evaluation data, through the collaborative action of structures such as bidirectional long short-term memory branches, linear transformation branches, and detection feature fusion branches, the performance index evaluation data can be processed in multiple dimensions. The conversion from qualitative to quantitative, feature fusion, and the transfer processing between multiple bidirectional long short-term memory branches make the evaluation of the pressure sensor performance more comprehensive, in-depth, and accurate, helping to more precisely identify the performance state of the pressure sensor, and providing a more reliable basis for the quality control, performance optimization, and reasonable application of the pressure sensor.

[0088] In a further technical solution, determining the detection element mapping relationship network based on the first relationship feature operation result between the first local detection element relationship network and the second local detection element relationship network includes: obtaining an intersection detection element relationship network; determining the fourth relationship feature operation result between the local association mapping relationship network corresponding to the first relationship feature operation result and the intersection detection element relationship network as the detection element mapping relationship network; wherein, the intersection detection element relationship network is used to determine the detection element mapping relationship network corresponding to each of the multiple detection attribute recognition units.

[0089] Determining the evaluation mapping relationship network based on the second relationship feature operation result between the first local evaluation relationship network and the second local evaluation relationship network includes: obtaining an intersection evaluation relationship network; determining the fifth relationship feature operation result between the local association mapping relationship network corresponding to the second relationship feature operation result and the intersection evaluation relationship network as the evaluation mapping relationship network; wherein, the intersection evaluation relationship network is used to determine the evaluation mapping relationship network corresponding to each of the multiple detection attribute recognition units.

[0090] Determining the performance correction mapping relationship network based on the third relationship feature operation result between the first local performance correction relationship network and the second local performance correction relationship network includes: obtaining an intersection performance correction relationship network; determining the sixth relationship feature operation result between the local association mapping relationship network corresponding to the third relationship feature operation result and the intersection performance correction relationship network as the performance correction mapping relationship network; wherein, the intersection evaluation relationship network is used to determine the performance correction mapping relationship network corresponding to each of the multiple detection attribute recognition units.

[0091] In this further technical solution, for the process of determining the detection element mapping relationship network, first, the detection element mapping relationship network is determined based on the first relationship feature operation result between the first local detection element relationship network and the second local detection element relationship network. In this process, an intersection detection element relationship network needs to be obtained. For example, the first local detection element relationship network may contain the relationships between some elements of the pressure sensor in accuracy detection and other characteristics of the sensor, such as the relationship between measurement error and the accuracy of the sensor chip; the second local detection element relationship network may involve the relationships between some elements in dynamic performance detection and other related factors, such as the relationship between frequency response and the internal structure of the sensor. The first relationship feature operation result is the result obtained by performing a specific operation between these two local relationship networks, and this operation is based on their internal logical associations.

[0092] Then, the determination of the fourth relationship feature operation result is carried out between the local association mapping relationship network corresponding to the first relationship feature operation result and the cross-detection element relationship network, and finally this result is determined as the detection element mapping relationship network. Among them, the cross-detection element relationship network has a special role. It is used to determine the detection element mapping relationship network corresponding to each of the multiple detection attribute recognition units. For example, there are three detection attribute recognition units. The cross-detection element relationship network will construct the detection element mapping relationship network in a way suitable for each detection attribute recognition unit according to the characteristics and requirements of different detection attribute recognition units. For example, for the first detection attribute recognition unit, if it mainly focuses on the repeatability aspect in static performance detection, the cross-detection element relationship network will screen and adjust the relationship content related to repeatability from the overall operation result to construct a part of the detection element mapping relationship network applicable to this detection attribute recognition unit.

[0093] For determining the evaluation mapping relationship network, operations are carried out based on the second relationship feature operation result between the first local evaluation relationship network and the second local evaluation relationship network. Similarly, the cross-evaluation relationship network is obtained first. The first local evaluation relationship network may include the relationship between the evaluation criteria of the step response index in dynamic performance detection under different application scenarios and other relevant factors (such as industry standards, cost limitations, etc.); the second local evaluation relationship network may include the relationship between the evaluation criteria of the temperature influence index in environmental adaptability detection under specific conditions and other relevant factors (such as the temperature range of the equipment operating environment, etc.). The second relationship feature operation result is the integrated operation result of these two local evaluation relationship networks.

[0094] Next, the determination of the fifth relationship feature operation result is carried out between the local association mapping relationship network corresponding to the second relationship feature operation result and the cross-evaluation relationship network, and it is determined as the evaluation mapping relationship network. The cross-evaluation relationship network is used to determine the evaluation mapping relationship network corresponding to each of the multiple detection attribute recognition units. For example, for example, there are two detection attribute recognition units. For the first detection attribute recognition unit, if it focuses on the frequency response evaluation in dynamic performance detection, the cross-evaluation relationship network will construct a part of the evaluation mapping relationship network related to the frequency response evaluation based on the overall operation result to meet the requirements of this detection attribute recognition unit for the evaluation mapping relationship network.

[0095] In determining the performance correction mapping relationship network, operations are performed based on the operation result of the third relationship feature between the first local performance correction relationship network and the second local performance correction relationship network. First, obtain the cross-performance correction relationship network. The first local performance correction relationship network may include the relationship between the correction strategy for the aging rate index in the durability stability detection and the sensor material characteristics and manufacturing process; the second local performance correction relationship network may include the relationship between the phase-frequency characteristic correction strategy in the dynamic performance detection and the signal processing algorithm and circuit design. The operation result of the third relationship feature is the operation result of these two local performance correction relationship networks.

[0096] Then, determine the operation result of the sixth relationship feature between the local association mapping relationship network corresponding to the operation result of the third relationship feature and the cross-performance correction relationship network, and determine it as the performance correction mapping relationship network. The cross-performance correction relationship network in the embodiment of the present invention is used to determine the performance correction mapping relationship network corresponding to each of the multiple detection attribute recognition units. For example, if there are four detection attribute recognition units, for the third detection attribute recognition unit, if it mainly involves the humidity impact correction in the environmental adaptability detection, the cross-performance correction relationship network will screen and construct the part of the performance correction mapping relationship network related to the humidity impact correction from the overall operation result to meet the requirements of this detection attribute recognition unit.

[0097] Based on the above technical solution, by introducing the cross-detection element relationship network, the cross-evaluation relationship network, and the cross-performance correction relationship network, it is possible to more accurately meet the different requirements of multiple detection attribute recognition units when constructing the detection element mapping relationship network, the evaluation mapping relationship network, and the performance correction mapping relationship network. This collaborative operation method of multiple relationship networks makes the construction of each mapping relationship network more meticulous, comprehensive, and targeted. For example, when constructing the detection element mapping relationship network for different detection attribute recognition units, relevant relationship content can be accurately extracted and adjusted from the overall operation result according to the focus of each unit, thereby improving the accuracy and effectiveness of the performance detection data processing of the pressure sensor and laying a solid foundation for more accurately evaluating the performance of the pressure sensor.

[0098] Under an optional technical concept, before obtaining the first performance detection response information in the multi-dimensional sensing performance detection data by the target recognition unit, it further includes: obtaining a first decision tree model, where the first decision tree model includes a plurality of cascaded sensing signal embedding mining components and a plurality of cascaded sensing signal embedding analysis components, and the sensing signal embedding mining components and the sensing signal embedding analysis components include cascaded bidirectional long short-term memory branches, linear transformation branches, and detection feature fusion branches; based on at least one signal attribute mapping relationship network paired with the bidirectional long short-term memory branch in the first decision tree model, determining at least one associated attribute mapping relationship network respectively paired with a plurality of the detection attribute recognition units in the bidirectional long short-term memory branch; adjusting the associated attribute mapping relationship network to obtain a plurality of attribute mapping feature subsets paired with the associated attribute mapping relationship network, where the relationship network sizes of the plurality of attribute mapping feature subsets are smaller than the relationship network size of the associated attribute mapping relationship network; updating at least one of the signal attribute mapping relationship networks paired with the bidirectional long short-term memory branch based on the plurality of attribute mapping feature subsets to obtain a second decision tree model; debugging the second decision tree model to obtain the target multi-variable decision tree, where the target multi-variable decision tree is used to process the pressure sensor detection data stream.

[0099] In some preferred embodiments, before debugging the second decision tree model to obtain the target multi-variable decision tree, it further includes: adjusting the sample fusion feature set paired with the detection feature fusion branch in the second decision tree model to obtain a plurality of local fusion feature sets matched with the sample fusion feature set, where the relationship network sizes of the plurality of local fusion feature sets are smaller than the relationship network size of the sample fusion feature set; using the plurality of local fusion feature sets to update the sample fusion feature set paired with the detection feature fusion branch to obtain the second decision tree model to be debugged.

[0100] Further, the second decision tree model is debugged to obtain the target multi - decision tree, where the target multi - decision tree is used to process the data stream detected by the pressure sensor, including: obtaining a historical detection data set, where the historical detection data set includes multiple data streams detected by the pressure sensor and training annotations paired with the multiple data streams detected by the pressure sensor respectively; using the historical detection data set to debug the second decision tree model; on the basis that the second decision tree model does not meet the debugging requirements, optimizing the model weights associated with the second decision tree model, where the model weights are model variables in the set of model variables indicated by the multiple attribute mapping feature subsets and the multiple local fusion feature sets; on the basis that the second decision tree model meets the debugging requirements, determining the second decision tree model as the target multi - decision tree.

[0101] Under this alternative technical idea, before obtaining the first performance detection response information in the multi - dimensional sensing performance detection data through the target recognition unit, an operation of constructing and training the target multi - decision tree is also included.

[0102] First, obtain a first decision tree model, which includes multiple cascaded sensing signal embedding mining components and multiple cascaded sensing signal embedding analysis components, and there are cascaded bidirectional long - short - term memory branches, linear transformation branches, and detection feature fusion branches in these components. For example, in the sensing signal embedding mining component, the bidirectional long - short - term memory branch may be responsible for processing the time - series related information in the data detected by the pressure sensor, the linear transformation branch performs linear transformation operations on the data, and the detection feature fusion branch fuses features from different sources.

[0103] Based on at least one signal attribute mapping relationship network paired with the bidirectional long - short - term memory branch in the first decision tree model, at least one associated attribute mapping relationship network paired with multiple detection attribute recognition units in the bidirectional long - short - term memory branch is determined. For example, in the first decision tree model, the signal attribute mapping relationship network stores the mapping relationship between the detection data processed by the bidirectional long - short - term memory branch and other related attributes. Through specific algorithms or rules, an associated attribute mapping relationship network related to each detection attribute recognition unit is determined. For example, for a certain detection attribute recognition unit that mainly focuses on the frequency response data in the dynamic performance of the pressure sensor, the associated attribute mapping relationship network will screen and adjust the mapping relationship part related to the frequency response from the signal attribute mapping relationship network.

[0104] Then, adjust the associated attribute mapping relationship network to obtain multiple attribute mapping feature subsets paired with the associated attribute mapping relationship network. The relationship network sizes of these attribute mapping feature subsets are smaller than that of the associated attribute mapping relationship network. For example, the associated attribute mapping relationship network may contain the complete mapping relationship of the frequency response from 10 Hz to 1000 Hz. After adjustment, the obtained attribute mapping feature subset may only focus on the frequency response mapping relationship from 100 Hz to 300 Hz, thus narrowing the scope of the relationship network and making it more targeted.

[0105] Update at least one signal attribute mapping relationship network paired with the bidirectional long short-term memory branch based on the multiple attribute mapping feature subsets to obtain the second decision tree model. This update operation makes the signal attribute mapping relationship network relied on by the bidirectional long short-term memory branch more accurate and efficient when processing data.

[0106] In some preferred embodiments, there are additional operations before debugging the second decision tree model. Adjust the sample fusion feature set paired with the detection feature fusion branch in the second decision tree model to obtain multiple local fusion feature sets matched with the sample fusion feature set. The relationship network sizes of these local fusion feature sets are smaller than that of the sample fusion feature set. For example, the sample fusion feature set contains the fusion features of various performance data such as the static performance, dynamic performance, environmental adaptability, and durability stability of the pressure sensor. The obtained local fusion feature set after adjustment may only focus on the fusion features of the dynamic performance and environmental adaptability, thereby narrowing the scope of the feature set.

[0107] Update the sample fusion feature set paired with the detection feature fusion branch using the multiple local fusion feature sets to obtain the second decision tree model to be debugged. This update operation makes the sample fusion feature set relied on by the detection feature fusion branch more in line with the requirements when processing data.

[0108] Furthermore, debug the second decision tree model to obtain the target multi-variable decision tree. First, obtain the historical detection data set, which contains multiple pressure sensor detection data streams and the training annotations paired with these data streams respectively. For example, the pressure sensor detection data stream may contain detection data in multiple aspects such as accuracy, repeatability, frequency response, and temperature influence, and the training annotation is the annotation of the performance of the pressure sensor corresponding to these detection data, such as good performance, medium, or poor.

[0109] Debug the second decision tree model using the historical detection data set. During the debugging process, if the second decision tree model does not meet the debugging requirements, optimize the model weights associated with the second decision tree model. The model weights in the embodiments of the present invention are the model variables in the set of model variables indicated by multiple attribute mapping feature subsets and multiple local fusion feature sets. For example, if the model has a large deviation in predicting the accuracy of the pressure sensor, adjust the model variable weights involved in the attribute mapping feature subset and local fusion feature set related to accuracy.

[0110] If the second decision tree model meets the debugging requirements, determine the second decision tree model as the target multi - decision tree, which is used to process the detection data stream of the pressure sensor.

[0111] In this way, through the gradual adjustment and optimization of the first decision tree model, including operations such as constructing the associated attribute mapping relationship network, attribute mapping feature subsets, and local fusion feature sets, the decision tree model becomes more accurate and efficient. When constructing the associated attribute mapping relationship network and attribute mapping feature subsets, it is possible to optimize for different detection attribute recognition units, improving the accuracy of the bidirectional long - short - term memory branch in processing data. When constructing the local fusion feature set, the data processing ability of the detection feature fusion branch is optimized. By using the historical detection data set for debugging and weight optimization, the accuracy and reliability of the model are further improved. The finally obtained target multi - decision tree can process the detection data stream of the pressure sensor more effectively, thereby providing a more accurate and reliable evaluation basis for the performance detection of the pressure sensor.

[0112] In an independent embodiment, before determining at least one associated attribute mapping relationship network paired with multiple detection attribute recognition units in the bidirectional long - short - term memory branch based on at least one signal attribute mapping relationship network paired with the bidirectional long - short - term memory branch in the first decision tree model, the following steps are cyclically implemented until a target down - sampling encoded feature is determined from multiple down - sampling encoded features, where each down - sampling encoded feature includes multiple adjustable model variables, and each adjustable model variable respectively indicates a round of model variable down - sampling processing performed on the first decision tree model. The model variable down - sampling processing includes at least one of feature sampling and feature update. The target down - sampling encoded feature is used to improve the first decision tree model into the second decision tree model: (1) Obtain multiple down - sampling encoded features obtained from the previous round of processing; (2) Process the first decision tree model respectively according to the multiple down - sampling encoded features to obtain associated decision tree models corresponding to the multiple down - sampling encoded features respectively; (3) Based on the target historical detection data set, obtain the decision analysis errors of each of the multiple associated decision tree models; (4) According to the decision analysis errors of each of the multiple associated decision tree models, determine the noise determination weight values paired with each of the multiple downsampled encoded features; (5) On the basis that the first downsampled encoded feature whose noise determination weight value meets the target threshold is not included in the multiple downsampled encoded features, determine at least one second downsampled encoded feature from the multiple downsampled encoded features based on the noise determination weight value; perform feature optimization on at least one of the second downsampled encoded features in sequence to obtain at least one optimized second downsampled encoded feature; add at least one optimized second downsampled encoded feature to the multiple downsampled encoded features; (6) On the basis that the first downsampled encoded feature whose noise determination weight value meets the target threshold is included in the multiple downsampled encoded features, determine the first downsampled encoded feature as the target downsampled encoded feature.

[0113] In this independent embodiment, before determining at least one associated attribute mapping relationship network paired with multiple detection attribute recognition units in the bidirectional long short-term memory branch based on at least one signal attribute mapping relationship network paired with the bidirectional long short-term memory branch in the first decision tree model, there is a loop operation to determine the target downsampled encoded feature, which is used to improve the first decision tree model into the second decision tree model.

[0114] First, the downsampled encoded feature contains multiple adjustable model variables, and each adjustable model variable respectively indicates a round of model variable downsampling processing performed on the first decision tree model, and this downsampling processing includes at least one of feature sampling and feature update.

[0115] At the beginning of the loop, obtain multiple downsampled encoded features obtained from the previous round of processing. For example, in the first round, there may be a set of initial downsampled encoded features, which are obtained by initially setting relevant variables in the first decision tree model based on certain rules.

[0116] Then, process the first decision tree model according to multiple downsampled encoded features respectively to obtain associated decision tree models corresponding to the multiple downsampled encoded features respectively. Taking the example mentioned above that the first decision tree model includes multiple cascaded sensing signal embedding mining components and multiple cascaded sensing signal embedding analysis components, after each downsampled encoded feature adjusts the relevant variables in these components, different associated decision tree models are obtained. These associated decision tree models may vary in structure and data processing methods due to different downsampled encoded features.

[0117] Then, based on the target historical detection dataset, obtain the decision analysis errors of each of the multiple associated decision tree models. The target historical detection dataset includes multiple pressure sensor detection data streams and training annotations paired with these data streams respectively. For example, when a certain associated decision tree model processes the accuracy detection data in the historical detection dataset, there may be a deviation from the accurate result in the training annotation, and this deviation can be the decision analysis error. For a historical detection dataset containing data in multiple aspects such as frequency response and temperature influence, the associated decision tree model will generate corresponding decision analysis errors when processing this data.

[0118] According to the decision analysis errors of each of the multiple associated decision tree models, determine the noise determination weights paired with each of the multiple downsampled encoded features. The larger the decision analysis error, the higher the corresponding noise determination weight may be, indicating that this downsampled encoded feature may introduce more "noise" or uncertainty in the model processing. For example, when an associated decision tree model processes the dynamic performance detection data of a pressure sensor and has a large decision analysis error, the noise determination weight of the corresponding downsampled encoded feature may be high.

[0119] On the basis that the first downsampled encoded feature whose noise determination weight meets the target threshold is not included in the multiple downsampled encoded features, determine at least one second downsampled encoded feature from the multiple downsampled encoded features based on the noise determination weight. The target threshold is a preset determination criterion. If the noise determination weights of no downsampled encoded features reach this criterion, then select some downsampled encoded features as the second downsampled encoded features according to the noise determination weight. Then, perform feature optimization on at least one second downsampled encoded feature in sequence to obtain at least one optimized second downsampled encoded feature. For example, adjust and optimize some model variables related to the dynamic performance detection data in the downsampled encoded features, such as adjusting the variable weights related to the frequency response. Add at least one optimized second downsampled encoded feature to the multiple downsampled encoded features for the next round of loop.

[0120] On the basis that the first downsampled encoded feature whose noise determination weight meets the target threshold is included in the multiple downsampled encoded features, determine the first downsampled encoded feature as the target downsampled encoded feature. Once the noise determination weight of a certain downsampled encoded feature reaches the target threshold, it is considered that this downsampled encoded feature meets the requirements and can be used as the target downsampled encoded feature for improving the first decision tree model into the second decision tree model.

[0121] It can be seen that by processing and screening the downsampled encoded features in a cyclic manner, the target downsampled encoded feature that is most suitable for improving the first decision tree model into the second decision tree model can be effectively determined from among numerous possible downsampled encoded features. In this process, determining the noise determination weight based on the decision analysis error can quantify the impact of each downsampled encoded feature on the model accuracy. Through the feature optimization and screening process, the quality of the downsampled encoded features is continuously improved. The finally obtained target downsampled encoded feature enables the improved second decision tree model to be more accurate and effective when processing pressure sensor detection data, laying a good foundation for subsequent operations such as constructing an associated attribute mapping relationship network, and improving the accuracy and reliability of the entire pressure sensor performance detection system.

[0122] In summary, in the embodiment of the present invention, the target recognition unit is first used to obtain the first performance detection response information from the multi-dimensional sensing performance detection data. This structure based on the target multi-decision tree detection attribute recognition branch can classify and recognize various performance detection data, ensuring the accuracy and pertinence of data acquisition. Then, by means of the target mapping relationship network paired with the target recognition unit, a confidence relationship list is determined to obtain the third performance detection response information, which can fully consider the complex relationships among the detection information and improve the accuracy of evaluation. The association recognition unit processes the second performance detection response information to obtain the fourth performance detection response information, and the multi-unit cooperation realizes the comprehensive analysis of different performance data. Finally, based on the third and fourth performance detection response information, the performance index evaluation data is determined, which can provide a comprehensive, accurate and scientific evaluation result for the pressure sensor performance, and is helpful for accurately controlling the pressure sensor performance in multiple links such as production, R & D, and use.

[0123] Further, Figure 2 FIG. shows a structural block diagram of a pressure sensor performance detection system 300, including: a memory 310 for storing program instructions and data; a processor 320 for being coupled to the memory 310 and executing the instructions in the memory 310 to implement the above method.

[0124] Further, a computer storage medium is also provided, which contains instructions that, when executed on a processor, implement the above method.

[0125] In several embodiments provided by the embodiments of the present invention, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device and method embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0126] In addition, each functional module in various embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0127] If the above functions are implemented in the form of software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program code. It should be noted that in this article, the term "including", "comprising", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or device including the said element.

[0128] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A pressure sensor performance detection method, characterized in that: The method is applied to a pressure sensor performance detection system, and the method comprises: Acquire first performance detection response information in the multidimensional sensing performance detection data through a target recognition unit, wherein the target recognition unit is a detection attribute recognition unit in a detection attribute recognition branch of a target multivariate decision tree, and the detection attribute recognition branch includes the target recognition unit and at least one associated recognition unit, and at least one associated recognition unit is used to process at least one second performance detection response information determined based on the multidimensional sensing performance detection data respectively; Determine a confidence relationship list paired with the first performance detection response information based on at least one target mapping relationship network paired with the target recognition unit, and determine third performance detection response information based on the first performance detection response information and the confidence relationship list, wherein a relationship network size of the target mapping relationship network matches a detection response vector size of the first performance detection response information; Acquire at least one fourth performance detection response information obtained by processing the second performance detection response information corresponding to each of the at least one association identification unit; Based on the third performance detection response information and at least one of the fourth performance detection response information, performance indicator evaluation data paired with the multi-dimensional sensing performance detection data is determined.

2. The method according to claim 1, characterized in that The determining, based on at least one target mapping relationship network paired with the target identification unit, a confidence relationship list paired with the first performance detection response information, and determining third performance detection response information based on the first performance detection response information and the confidence relationship list, includes: Determine a detection element mapping relationship network, an evaluation mapping relationship network, and a performance correction mapping relationship network included in at least one of the target mapping relationship networks, wherein the network sizes of the detection element mapping relationship network, the evaluation mapping relationship network, and the performance correction mapping relationship network match the detection response vector size of the first performance detection response information; Determine a response element mapping knowledge set based on the first performance detection response information and the detection element mapping relationship network, and determine a response evaluation mapping knowledge set based on the first performance detection response information and the evaluation mapping relationship network; Determining the confidence relationship list paired with the first performance detection response information according to the response element mapping knowledge set and the response evaluation mapping knowledge set; Based on the first performance detection response information and the performance correction mapping relationship network, a response correction mapping knowledge set is determined, and the third performance detection response information is determined according to the confidence relationship list and the response correction mapping knowledge set.

3. The method according to claim 2, characterized in that Before obtaining at least one fourth performance detection response information obtained by processing the second performance detection response information corresponding to the respective one of the association identification units, the method further includes: Obtaining the uth second performance detection response information in the multi-dimensional sensing performance detection data through the uth association identification unit, wherein u is an integer not less than 1 and not greater than X, and X is the number of the association identification units included in the detection attribute identification branch; Based on at least one association mapping relationship network paired with the u-th association identification unit, determine the confidence relationship list paired with the u-th second performance detection response information, and determine the u-th fourth performance detection response information based on the u-th second performance detection response information and the confidence relationship list.

4. The method according to claim 2, characterized in that The determining, based on the third performance detection response information and at least one of the fourth performance detection response information, performance indicator evaluation data paired with the multi-dimensional sensing performance detection data comprises: combining a third performance detection response vector set used to represent the third performance detection response information and at least one fourth performance detection response vector set used to represent at least one fourth performance detection response information to obtain a linkage performance detection response vector set; The linkage performance detection response vector set and the attribute mapping relationship network paired with the detection attribute identification branch are used to determine an indicator evaluation viewpoint label set for characterizing the performance indicator evaluation data.

5. The method according to claim 2, characterized in that The determining of the detection element mapping relationship network, the evaluation mapping relationship network and the performance correction mapping relationship network included in at least one of the target mapping relationship networks comprises at least one of the following: Acquire a first local detection element relationship network and a second local detection element relationship network, and determine the detection element mapping relationship network based on a first relationship feature operation result between the first local detection element relationship network and the second local detection element relationship network; Acquire a first local evaluation relationship network and a second local evaluation relationship network, and determine the evaluation mapping relationship network based on a second relationship feature operation result between the first local evaluation relationship network and the second local evaluation relationship network; A first local performance correction relationship network and a second local performance correction relationship network are obtained, and the performance correction mapping relationship network is determined based on a third relationship feature calculation result between the first local performance correction relationship network and the second local performance correction relationship network.

6. The method according to claim 5, characterized in that After determining the performance indicator evaluation data paired with the multi-dimensional sensing performance detection data based on the third performance detection response information and at least one of the fourth performance detection response information, the method includes: On the basis that the detection attribute recognition branch is a bidirectional long short-term memory branch in the target multivariate decision tree, the performance indicator evaluation data is processed based on a linear transformation branch connected to the bidirectional long short-term memory branch to obtain performance detection linear quantization data; Determine a target fusion feature set based on a first local fusion feature set and a second local fusion feature set paired with a detection feature fusion branch; Processing the performance detection linear quantization data based on the target fusion feature set to obtain target performance detection data; On the basis that the bidirectional long short-term memory branch is the last bidirectional long short-term memory branch in the target multivariate decision tree, determining a detection attribute recognition result based on the target performance detection data; On the basis that the bidirectional long short-term memory branch is not the last bidirectional long short-term memory branch in the target multivariate decision tree, the target performance detection data is input into the next bidirectional long short-term memory branch.

7. The method according to claim 5, characterized in that The method of determining the detection element mapping relationship network based on the first relationship feature operation result between the first local detection element relationship network and the second local detection element relationship network includes: obtaining a cross detection element relationship network; determining the detection element mapping relationship network as the detection element mapping relationship network by calculating the fourth relationship feature operation result between the local association mapping relationship network corresponding to the first relationship feature operation result and the cross detection element relationship network; wherein the cross detection element relationship network is used to determine the detection element mapping relationship network corresponding to each of the plurality of detection attribute recognition units; The step of determining the evaluation mapping relationship network based on the second relationship feature calculation result between the first local evaluation relationship network and the second local evaluation relationship network includes: obtaining a cross-evaluation relationship network; determining the evaluation mapping relationship network by calculating the fifth relationship feature calculation result between the local association mapping relationship network corresponding to the second relationship feature calculation result and the cross-evaluation relationship network; wherein the cross-evaluation relationship network is used to determine the evaluation mapping relationship network corresponding to each of the plurality of detection attribute recognition units; The performance correction mapping relationship network is determined based on the third relationship feature calculation result between the first local performance correction relationship network and the second local performance correction relationship network, including: obtaining a cross-performance correction relationship network; determining the performance correction mapping relationship network as the performance correction mapping relationship network using the sixth relationship feature calculation result between the local association mapping relationship network corresponding to the third relationship feature calculation result and the cross-performance correction relationship network; wherein the cross-evaluation relationship network is used to determine the performance correction mapping relationship network corresponding to each of multiple detection attribute identification units.

8. The method according to claim 1, characterized in that Before obtaining the first performance detection response information in the multi-dimensional sensing performance detection data by the target recognition unit, the method further includes: Acquire a first decision tree model, wherein the first decision tree model includes a plurality of cascaded sensor signal embedding mining components and a plurality of cascaded sensor signal embedding analysis components, and the sensor signal embedding mining components and the sensor signal embedding analysis components include cascaded bidirectional long short-term memory branches, linear transformation branches and detection feature fusion branches; Based on at least one signal attribute mapping relationship network paired with the bidirectional long short-term memory branch in the first decision tree model, determining at least one associated attribute mapping relationship network paired with the plurality of detection attribute recognition units in the bidirectional long short-term memory branch; Adjusting the associated attribute mapping relationship network to obtain a plurality of attribute mapping feature subsets paired with the associated attribute mapping relationship network, wherein the relationship network size of each of the plurality of attribute mapping feature subsets is smaller than the relationship network size of the associated attribute mapping relationship network; Based on the plurality of attribute mapping feature subsets, at least one of the signal attribute mapping relationship networks paired with the bidirectional long short-term memory branches is updated to obtain a second decision tree model; Debugging the second decision tree model to obtain the target multivariate decision tree, wherein the target multivariate decision tree is used to process the pressure sensor detection data stream; Before debugging the second decision tree model to obtain the target multivariate decision tree, the method further includes: Adjusting the sample fusion feature set paired with the detection feature fusion branch in the second decision tree model to obtain a plurality of local fusion feature sets matching the sample fusion feature set, wherein the relationship network size of each of the plurality of local fusion feature sets is smaller than the relationship network size of the sample fusion feature set; Using a plurality of the local fusion feature sets to update the sample fusion feature set paired with the detection feature fusion branch, to obtain the second decision tree model to be debugged; The debugging of the second decision tree model to obtain the target multivariate decision tree, wherein the target multivariate decision tree is used to process the pressure sensor detection data stream, including: Acquire a historical detection data set, wherein the historical detection data set includes a plurality of pressure sensor detection data streams and training annotations respectively paired with the plurality of pressure sensor detection data streams; Debugging the second decision tree model using the historical detection data set; On the basis that the second decision tree model does not meet the debugging requirements, optimizing the model weights associated with the second decision tree model, wherein the model weights are model variables in the model variable set indicated by the plurality of attribute mapping feature subsets and the plurality of local fusion feature sets; On the basis that the second decision tree model meets the debugging requirements, the second decision tree model is determined as the target multivariate decision tree.

9. A pressure sensor performance detection system, characterized in that: include: Memory, used to store program instructions and data; A processor, coupled to a memory, and configured to execute instructions in the memory to implement the method according to any one of claims 1 to 8.

10. A computer storage medium, characterized in that: Contains instructions, which, when executed on a processor, implement the method according to any one of claims 1 to 8.

Images