Instruction execution state analysis method and system fusing multi-sensor measurement data

Abstract

This invention relates to a method and system for analyzing the execution status of commands by fusing multi-sensor measurement data. The method includes the following steps: S10, performing random error analysis on the measurement data of each parameter to determine singular intervals and detect singular points; a singular interval refers to a data segment containing singular points; S20, segmenting the time series of measurement data using singular points and performing statistical analysis on the segmented data; S30, fusing the singular intervals, characteristic intervals, and non-characteristic intervals of all parameters with consistent effective time periods; S40, determining whether the characteristic interval is a fault interval and whether the singular points in the non-characteristic interval are fault points. This invention not only improves analysis efficiency but also enhances the accuracy of analysis results, avoiding missed or false judgments.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for analyzing the execution status of instructions by fusing multi-sensor measurement data. Background Technology

[0002] In space missions, the operating procedures of automated equipment have strict design processes and requirements. In order to effectively and quickly grasp the operating status of the equipment, it is necessary to accurately and timely analyze the measurement data of the operating status of the equipment in order to complete the assessment of the operating status of the equipment.

[0003] The data of automated equipment is mainly divided into two categories: (1) the design data of the automated equipment operation process, which is pre-loaded into the computer program and executed by the equipment computer; (2) the measurement data during the operation of the automated equipment, which is time-based measurement data, i.e., time series. The data of category (1) is called standard design data, and the data of category (2) is the actual measurement data during the operation of the equipment. By analyzing the data of category (2) and comparing it with the data of category (1), it is determined whether the equipment operates according to the design program.

[0004] Because equipment generates a wide variety of measurement data, especially large-scale automated equipment, which can generate hundreds or even thousands of data points, and each data point is sampled frequently and for long periods, a single batch of measurement data can generate tens of thousands of frames. The trends of these different measurement data points vary considerably, and the design value range also varies significantly. Data analysis revealed that even if the design value for a particular measurement data point is fixed, the actual measurement result may not equal this design value due to environmental factors such as temperature, noise, and vibration during sensor data acquisition; instead, it may fluctuate around this value. Data collected by different sensors for the same component also shows some differences and is not entirely identical. Furthermore, the measurement results for the same sampling parameter in different batches are not the same. Manually judging each frame of each measurement data point—analyzing whether it jumps according to the program design and whether the values ​​at different times are consistent with the design value—requires experienced professionals to spend a significant amount of time on this analysis, resulting in low efficiency. Moreover, manual analysis is prone to omissions and misjudgments. Summary of the Invention

[0005] The purpose of this invention is to improve the problems of low efficiency and low accuracy of manual judgment, and to provide a method and system for analyzing the command execution status by integrating multi-sensor measurement data. This method can not only achieve automated judgment and improve efficiency, but also improve accuracy.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A method for analyzing instruction execution status by fusing measurement data from multiple sensors includes the following steps:

[0008] S10, Perform random error analysis on the measurement data of each obtained parameter to determine the singular interval and detect singular points; the singular interval refers to the data segment containing singular points;

[0009] S20 uses singular points as the basis for segmentation, divides the measurement data into segments, and statistically analyzes the mean, maximum, minimum, variance, and standard deviation of each data segment.

[0010] S30, merge the singular intervals of all parameters with the same valid data period to determine the characteristic interval and non-characteristic interval;

[0011] S40: Compare the occurrence time of the characteristic interval with the preset instruction time of the program. If they match, the characteristic interval is determined to be the equipment response control program time. If they do not match, the singular point of the characteristic interval is determined to be the fault point. If they match, the equipment instruction action is determined to have occurred. For non-characteristic intervals, determine whether the mean, maximum, minimum, variance, and standard deviation of the two data segments before and after the singular point meet the design index requirements. If they all meet the requirements, the singular point is an outlier. If any index item of any data segment does not meet the requirements, the singular point is a fault point.

[0012] Step S10 includes:

[0013] S101, divide the measurement data into multiple data segments according to the set time step;

[0014] S102, calculate the random error for each data segment, we have t represents the piecewise step size, n is the number of points, and p is the difference order;

[0015] S103, Determine If the condition is met, then the current data segment is determined to be a singular interval. For the current data segment T j random error For the previous data segment T j-1 Random error;

[0016] S104, for singular intervals, determine... Is it true? If so, then determine. It is a singular point; Let i represent the measurement data of the i-th data point, where i = 1, 2, 3, ..., n.

[0017] The processing in step S30 includes: for measurement data with consistent valid time periods, determining whether there are identical singular intervals; if so, and the proportion of parameters with identical singular intervals is greater than or equal to a set threshold, then this singular interval is determined to be a feature interval; otherwise, it is determined to be a non-feature interval.

[0018] In step S40, when determining whether the occurrence time of the feature interval is consistent with the preset instruction time of the program, it is a determination... Whether it is true or false, if true, it is considered consistent; otherwise, it is considered inconsistent. TKThe TKActive sets the preset instruction time for the program. To allow for a range of motion deviations.

[0019] A command execution status analysis system that integrates multi-sensor measurement data includes:

[0020] The random error analysis module is used to perform random error analysis on the measurement data of each parameter, determine the singular interval, and detect singular points; the singular interval refers to the data segment containing singular points.

[0021] The statistical analysis module is used to segment the measurement data based on singular points and to statistically analyze the mean, maximum, minimum, variance, and standard deviation of each data segment.

[0022] The fusion analysis module is used to fuse the singular intervals of all parameters with the same valid time period of the data to determine the characteristic intervals and non-characteristic intervals.

[0023] The execution status analysis module compares the occurrence time of a characteristic interval with the preset instruction time of the program. If they match, the characteristic interval is determined to be the time of the equipment response control program. If they do not match, the characteristic interval is determined to be a fault point. If they match, the equipment instruction action is determined to have occurred. For non-characteristic intervals, it is determined whether the mean, maximum, minimum, variance, and standard deviation of the two data segments before and after the singular point meet the design index requirements. If they all meet the requirements, the singular point is an outlier. If any index item of any data segment does not meet the requirements, the singular point is a fault point.

[0024] A computer program product includes computer-readable instructions that, when executed by a processor, implement the steps in the instruction execution state analysis method for fusing multi-sensor measurement data described in this invention.

[0025] A computer-readable storage medium including computer-readable instructions, which, when executed by a processor, implement the steps in the instruction execution state analysis method for fusing multi-sensor measurement data described in this invention.

[0026] An electronic device is characterized by comprising: a memory for storing program instructions; and a processor connected to the memory for executing the program instructions in the memory to implement the steps in the instruction execution state analysis method for fusing multi-sensor measurement data described in this invention.

[0027] Compared with existing technologies, this invention can achieve automated analysis, greatly improving the processing efficiency of manual analysis. It can also avoid missed judgments and human errors. Moreover, based on statistical analysis methods, it detects all measurement parameters, finds outliers, and uses the outliers of each measurement parameter to segment the time series of measurement data. It judges whether the mean, variance, and other indicators of each segment of data meet the requirements. The method not only analyzes the variation law of the measurement data itself, but also judges the numerical value of the measurement data, which has high reliability and can improve the accuracy of the analysis results. Attached Figure Description

[0028] Figure 1 This is a flowchart of a method for analyzing the execution status of instructions by fusing multi-sensor measurement data, as provided in this embodiment.

[0029] Figure 2 This is a diagram illustrating the effect of determining the occurrence of a device action command in an example.

[0030] Figure 3 This is a block diagram of an instruction execution status analysis system that integrates multi-sensor measurement data, as provided in this embodiment.

[0031] Figure 4 This is a block diagram of an electronic device provided in the embodiment. Detailed Implementation

[0032] The technical solution of the present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0033] You can refer to this. Figure 1 The flowchart shown in this embodiment illustrates a method for analyzing the execution status of instructions by fusing multi-sensor measurement data, comprising the following steps:

[0034] S10, perform random error analysis on the measurement data of each parameter to determine the singular interval and detect the singular point; the singular interval refers to the data segment containing the singular point. The singular point determination is defined as the determination that the data measured by a certain sensor in the whole operation of the equipment has a discrete point or inflection point. That is, the singular point is the discrete point or inflection point in the measurement data.

[0035] S20 uses singular points as the basis for segmentation, divides the measurement data into segments, and statistically analyzes the mean, maximum, minimum, variance, and standard deviation of each data segment.

[0036] S30, merge the singular intervals of all parameters with the same valid data period to determine the characteristic interval and non-characteristic interval;

[0037] S40: Compare the occurrence time of the characteristic interval with the preset instruction time of the program. If they match, the characteristic interval is determined to be the time of the equipment response control program. If they do not match, the singular point of the characteristic interval is determined to be the fault point. If they match, the equipment instruction action is determined to have occurred, that is, the equipment executes the preset instruction of the program. For non-characteristic intervals, determine whether the mean, maximum, minimum, variance, and standard deviation of the two data segments before and after the singular point meet the design index requirements. If they all meet the requirements, the singular point is an outlier. If any index item of any data segment does not meet the requirements, the singular point is a fault point.

[0038] In automated equipment systems, various types of sensors are typically required to collect different measurement data and work together to complete automated control. The method described above integrates and analyzes various types of measurement data to determine whether the equipment executes the command operation or whether a fault has occurred.

[0039] In the data analysis process, it is essential to first understand the meaning of the data representation, such as: which part of the equipment the data is from, the working time period, the time period the data represents, and the design value of the data. Only by analyzing these attributes of the data can the correctness of the measurement data be determined. Therefore, in step S10 above, after obtaining the measurement data for each parameter, the measurement data is first cataloged using the following metadata standard: {ChName, ParaName, DataSource, DataType, EfTimeStart, EfTimeEnd, TimePeri, Value, MeasurePart}, where ChName represents the Chinese name, ParaName represents the data code, DataSource represents the data source, DataType represents the data type, EfTimeStart represents the start time of the valid data period (the valid data period refers to the sensor's working time period), EfTimeEnd represents the end time of the valid data period, TimePeri represents the working time period, Value represents the data design value, and MeasurePart represents the sensor measurement part.

[0040] Random error refers to an error that, under certain observation conditions, exists when measurements are repeated multiple times over a time series. Its value or sign is not fixed and it shows no regular pattern of change, but overall it conforms to certain statistical characteristics (such as mean, variance, and distribution). Although random error appears irregular and unpredictable on the surface and in individual cases, and therefore cannot be eliminated, its statistical characteristics can be obtained through extensive measurement and analysis. Therefore, it has high reliability for analyzing instruction execution status.

[0041] For each parameter's measurement data, random error analysis is required. Specifically, in step S10 above, the random error analysis process includes:

[0042] S101 divides the measurement data into multiple data segments according to a set time step. Since the sensor's measurement data is sampled at a certain frequency and is a time series, each data segment is a time series.

[0043] S102, calculate the random error for each data segment, we have t represents the piecewise step size, n is the number of points, and p is the difference order. Based on the experimental data analysis, we take... , .in The calculation method is as follows: In actual calculations, when the accumulation point is greater than... At that time, the accumulation begins. Then, always keep 13 latest data points, and increment i by 1 for each new data point. When i=n, ​​the random error σA is obtained.

[0044] S103, According to probability theory, 95% of the data values ​​in a sequence will fall into... The interval is defined, therefore, it is necessary to determine whether the random error between the current data segment and the previous data segment is greater than 3 times, i.e., to determine... If the condition is true, then the current data segment is determined to be a singular interval. For the current data segment T j random error, For the previous data segment T j-1 random error, .

[0045] S104, for singular intervals, make a judgment. Is it true? If so, then determine. It is a singular point. (i=1, 2, 3, ..., n) represents the measurement data of the i-th data point.

[0046] The random error of a singular interval changes significantly from that of adjacent time series. The determination of a parameter singularity point is defined as the identification of a discrete point or inflection point in the data measured by a certain sensor during the entire operation of the device. When the random errors of adjacent data segments differ by a factor of three, it indicates a high probability of the existence of a singular point, and therefore it is determined to be a singular interval. For The established data segment adopts Detection and measurement data (i=1, 2, 3…), if the condition is met, then determine… It is a singular point.

[0047] The singular points contained within a singular interval could be points where the equipment executes commands, outliers, or points where the equipment malfunctions. To determine whether a point is an outlier (an outlier is an observation that is significantly larger or smaller than the true value, with a deviation far exceeding the accuracy range), all measurement data are retrieved. Parameters with consistent valid data periods are examined to determine if they share the same singular interval. If all parameters with consistent valid data periods share a common singular interval, or if the number of parameters with the same singular interval reaches a certain proportion of the number of parameters with consistent valid data periods (this proportion is an indicator of equipment reliability), then the singular points within this singular interval are considered not outliers, and this singular interval is determined as a characteristic interval.

[0048] Therefore, in step S30 above, fusing the singular intervals of all parameters involves analyzing all measurement data with consistent effective times to determine if there are identical singular intervals, i.e., singular intervals occurring at the same time. If all measurement data have identical singular intervals (possibly one or more), or if the proportion of parameters with identical singular intervals is greater than or equal to a set threshold (based on experimental results, this threshold can be 0.66), then this singular interval is determined to be a characteristic interval. Singular intervals that do not meet the above conditions are determined to be non-characteristic intervals.

[0049] In practical implementation, the following program modules can be used:

[0050] While (all measurement parameters)

[0051] {

[0052] if(ParaName m .EfTimeStart==ParaName n .EfTimeStart) and(ParaName m .EfTimeEnd==ParaName n .EfTimeEnd)

[0053] {

[0054] NCoutEffctTimeEqual++;

[0055] if(ParaName m .T j .Tsta< <ParaName n .T j .Tsta and ParaName m .T j .Tend≥ParaName n .T j .Tsta)

[0056] {

[0057] NCoutCharaTimeEqual++;

[0058] Save the parameter name ParaName and the singular interval T j ;

[0059] }

[0060] else if(ParaName m .T j .Tsta≥ParaName n .T j .Tsta and ParaName m .T j .Tend≤ParaName n .T j .Tsta)

[0061] {

[0062] NCoutCharaTimeEqual++;

[0063] Save the parameter name ParaName and the singular interval T j ;

[0064] }

[0065] }

[0066] if(NCoutCharaTimeEqual / NCoutCharaTimeEqual> )

[0067] {

[0068] Remember T i The characteristic interval;

[0069] }

[0070] This represents the percentage of the number of identical parameters in singular intervals relative to the total number of parameters within the same valid data time period.

[0071] In step S40 above, when determining whether the occurrence time of the feature interval is consistent with the preset instruction time of the program, it is a determination... Whether it is true or not, if it is true, then it is consistent; otherwise, it is inconsistent. Preset instruction times for the program. The occurrence time of the characteristic interval. To allow for a range of motion deviations.

[0072] For non-feature intervals, the maximum, minimum, mean, variance, and standard deviation (these five indicators are used in this embodiment; other implementations may use more or fewer indicators) of the two data segments before and after the singular point of the singular interval are analyzed. If all indicators of the two data segments meet the design requirements, the singular point is an outlier; if any indicator of any data segment does not meet the design requirements, the singular point is a fault point. For example, the maximum value indicator in the data segment before the singular point does not meet the corresponding design requirements; or the variance and standard deviation indicators in the data segment after the singular point do not meet the corresponding design requirements; or the maximum value indicator in the data segment before the singular point does not meet the corresponding design requirements, and the mean indicator in the data segment after the singular point does not meet the corresponding design requirements; all these cases are judged as the singular point being a fault point.

[0073] like Figure 2 As shown, in a certain experimental case, the equipment control program presets the command action time to time t2. Random error analysis and statistical analysis are performed on all measurement data of the equipment's operating status to detect singular intervals and singular points: measurement parameters The singular intervals are A and B, and the singular points are a and b. The measured parameters are segmented based on the singular points. The entire time series is divided into three data segments: t1-t2, t2-t6, and t6-t7. Calculate the mean, maximum, minimum, variance, and standard deviation of each data segment; measure parameters. The singular intervals are C, D, and E, and the singular points are c, d, and e. The measured parameters... The entire time series is divided into four data segments: t1-t2, t2-t4, t4-t6, and t6-t7. Calculate the mean, maximum, minimum, variance, and standard deviation of the four data segments. The singular intervals are F and G, and the singular points are f and g. Measurement parameters... The entire time series is divided into three data segments: t1-t2, t2-t5, and t5-t7. The mean, maximum, minimum, variance, and standard deviation of the three data segments are calculated. The effective time period for the three measured parameters is from t1 to t7.

[0074] 1) The occurrence times of singular intervals A, C, and F are consistent, and all three parameters occur at time t2. Therefore, singular intervals A, C, and F can be identified as characteristic intervals. At the same time, t2 is the preset instruction action time of the program. Therefore, it can be identified that the device response control program instruction action occurs at time t2.

[0075] 2) The occurrence times of singular intervals B and E are consistent. Two of the three parameters have the same singular interval at time t6, which satisfies the condition that the proportion is not less than 60%. Therefore, singular intervals B and E can be determined as characteristic intervals. However, t6 is not the preset instruction action time of the program. Therefore, it can be determined that the equipment malfunctions at time t6.

[0076] 3) The singular interval D occurs at time t4, and this singular interval is only a parameter. The occurrence of the singularity does not meet the condition of a proportion of not less than 60%, therefore, the singular interval D can be determined as a non-characteristic interval. Furthermore, the mean, maximum, minimum, variance, and standard deviation of the two data segments t2-t4 and t4-t6 before and after the singular point meet the design requirements. Therefore, the parameters... At time t4, there is an outlier, which is a singular point d. Similarly, it can be determined that the singular interval G is a non-characteristic interval. (Parameter) At time t5, there is a wild value, which is the singular point g.

[0077] See also Figure 3 Based on the same inventive concept, this embodiment also provides an instruction execution status analysis system that integrates multi-sensor measurement data, including:

[0078] The random error analysis module is used to perform random error analysis on the measurement data of each parameter, determine the singular interval, and detect singular points; the singular interval refers to the data segment containing singular points.

[0079] The statistical analysis module is used to segment the measurement data based on singular points and to statistically analyze the mean, maximum, minimum, variance, and standard deviation of each data segment.

[0080] The fusion analysis module is used to fuse the singular intervals of all parameters with the same valid time period of the data to determine the characteristic intervals and non-characteristic intervals.

[0081] The execution status analysis module compares the occurrence time of a characteristic interval with the preset instruction time of the program. If they match, the characteristic interval is determined to be the time of the equipment response control program. If they do not match, the characteristic interval is determined to be a fault point. If they match, the equipment instruction action is determined to have occurred. For non-characteristic intervals, it is determined whether the mean, maximum, minimum, variance, and standard deviation of the two data segments before and after the singular point meet the design index requirements. If they all meet the requirements, the singular point is an outlier. If any index item of any data segment does not meet the requirements, the singular point is a fault point.

[0082] For details on the specific execution of each module, please refer to the relevant descriptions in the aforementioned method steps; they will not be repeated here.

[0083] like Figure 4As shown, this embodiment also provides an electronic device that may include a processor and a memory, wherein the memory is coupled to the processor. It is worth noting that this figure is exemplary, and other types of structures can be used to supplement or replace this structure to achieve data extraction, report generation, communication, or other functions.

[0084] like Figure 4 As shown, the electronic device may also include an input unit, a display unit, and a power supply 45. It is worth noting that the electronic device is not necessarily required to include these components. Figure 4 All components shown in the image. Furthermore, electronic devices may also include... Figure 4 For components not shown, please refer to existing technologies.

[0085] A processor, sometimes also called a controller or operating control, may include a microprocessor or other processor device and / or logic device that receives input and controls the operation of various components of an electronic device.

[0086] The memory may be one or more of the following: a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store information such as the processor's configuration information and the instructions executed by the processor. The processor can execute programs stored in the memory to perform information storage or processing. In one embodiment, the memory also includes a buffer memory, or buffer, to store intermediate information.

[0087] This invention also provides a computer program product including computer-readable instructions. When the computer-readable instructions are executed in an electronic device, the program product causes the electronic device to perform the operation steps included in the method of this invention.

[0088] This invention also provides a storage medium storing computer-readable instructions that cause an electronic device to perform the operation steps included in the method of this invention.

[0089] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0090] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it 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 all or part of the 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0091] The above specific embodiments are merely several optional embodiments of the present invention. Based on the technical solutions of the present invention and the relevant teachings of the above embodiments, those skilled in the art can make various alternative improvements and combinations to the above specific embodiments.

Claims

1. A method for analyzing the execution status of instructions by fusing measurement data from multiple sensors, characterized in that, Includes the following steps: S10, Perform random error analysis on the measurement data of each obtained parameter to determine the singular interval and detect singular points; the singular interval refers to the data segment containing singular points; S20 uses singular points as the basis for segmentation, divides the measurement data into segments, and statistically analyzes the mean, maximum, minimum, variance, and standard deviation of each data segment. S30, merge the singular intervals of all parameters with the same valid data period to determine the characteristic interval and non-characteristic interval; S40: Compare the occurrence time of the characteristic interval with the preset instruction time of the program. If they match, the characteristic interval is determined to be the equipment response control program time. If they do not match, the singular point of the characteristic interval is determined to be the fault point. If they match, the equipment instruction action is determined to have occurred. For non-characteristic intervals, determine whether the mean, maximum, minimum, variance, and standard deviation of the two data segments before and after the singular point meet the design index requirements. If they all meet the requirements, the singular point is an outlier. If any index item of any data segment does not meet the requirements, the singular point is a fault point.

2. The instruction execution state analysis method based on multi-sensor measurement data according to claim 1, characterized in that, Step S10 includes: S101, divide the measurement data into multiple data segments according to the set time step; S102, calculate the random error for each data segment, we have t represents the piecewise step size, n is the number of points, and p is the difference order; S103, Determine If the condition is met, then the current data segment is determined to be a singular interval. For the current data segment T j random error For the previous data segment T j-1 Random error; S104, for singular intervals, determine... Is it true? If so, then determine. It is a singular point; Let i represent the measurement data of the i-th data point, where i = 1, 2, 3, ..., n.

3. The instruction execution state analysis method based on multi-sensor measurement data according to claim 2, characterized in that, In step S102, when the accumulation point is greater than At that time, the accumulation begins. Then, always keep 13 latest data points, and increment i by 1 for each new data point. When i=n, ​​the random error σA is obtained.

4. The instruction execution state analysis method based on multi-sensor measurement data according to claim 1, characterized in that, The processing in step S30 includes: for measurement data with consistent valid time periods, determining whether there are identical singular intervals; if so, and the proportion of parameters with identical singular intervals is greater than or equal to a set threshold, then this singular interval is determined to be a feature interval; otherwise, it is determined to be a non-feature interval.

5. The instruction execution state analysis method based on multi-sensor measurement data according to claim 1, characterized in that, In step S40, when determining whether the occurrence time of the feature interval is consistent with the preset instruction time of the program, it is a determination... Whether it is true or false is determined; if it is true, it is considered consistent; otherwise, it is considered inconsistent. TKThe is the program's preset instruction time, and TKActive is the occurrence time of the feature interval. To allow for a range of motion deviations.

6. A command execution status analysis system that integrates multi-sensor measurement data, characterized in that, include: The random error analysis module is used to perform random error analysis on the measurement data of each parameter, determine the singular interval, and detect singular points. A singular interval is a data segment containing singular points; The statistical analysis module is used to segment the measurement data based on singular points and to statistically analyze the mean, maximum, minimum, variance, and standard deviation of each data segment. The fusion analysis module is used to fuse the singular intervals of all parameters with the same valid time period of the data to determine the characteristic intervals and non-characteristic intervals. The execution status analysis module compares the occurrence time of a characteristic interval with the preset instruction time of the program. If they match, the characteristic interval is determined to be the time of the equipment response control program. If they do not match, the characteristic interval is determined to be a fault point. If they match, the equipment instruction action is determined to have occurred. For non-characteristic intervals, it is determined whether the mean, maximum, minimum, variance, and standard deviation of the two data segments before and after the singular point meet the design index requirements. If they all meet the requirements, the singular point is an outlier. If any index item of any data segment does not meet the requirements, the singular point is a fault point.

7. The instruction execution status analysis system that integrates multi-sensor measurement data according to claim 6, characterized in that, The random error analysis module first divides the measurement data into multiple data segments according to a set time step, and then uses the formula... Calculate the random error for each data segment, where t represents the segmentation step size, n is the number of points, and p is the difference order; finally, determine... If the condition is true, then the current data segment is determined to be a singular interval. For singular intervals, the following checks are performed: Is it true? If so, then determine. It is a singular point; T j T j-1 random error, Let i represent the measurement data of the i-th data point, where i = 1, 2, 3, ..., n.

8. A computer program product comprising computer-readable instructions, characterized in that, When the computer-readable instructions are executed by the processor, they implement the steps in the instruction execution state analysis method for fusing multi-sensor measurement data as described in any one of claims 1-5.

9. A computer-readable storage medium comprising computer-readable instructions, characterized in that, When the computer-readable instructions are executed by the processor, they implement the steps in the instruction execution state analysis method for fusing multi-sensor measurement data as described in any one of claims 1-5.

10. An electronic device, characterized in that, include: Memory, which stores program instructions; The processor, connected to the memory, executes program instructions in the memory to implement the steps in the instruction execution state analysis method for fusing multi-sensor measurement data as described in any one of claims 1-5.

Images