CN116484306B - Positioning method and device of abnormal sensor, computer equipment and storage medium - Google Patents

Abstract

The application provides a positioning method, a device, computer equipment and a storage medium of an abnormal sensor, wherein the method comprises the following steps: acquiring first operation parameters of a plurality of sensors at different moments; grouping a plurality of sensors according to the association relation; determining a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to the first operation parameters of each sensor in the same group; obtaining second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors; determining the group of sensors as an abnormal sensor group under the condition that the average value of the change rate of the second operation parameters of the sensors exceeds a corresponding threshold value; an anomaly sensor is determined from each of the sensors in the anomaly sensor group based on a correlation between the first and second syndromes of the anomaly sensor group. The method can effectively locate the abnormal sensor on line, gets rid of dependence on data, and has high abnormality discrimination and locating precision.

Description

Positioning method and device of abnormal sensor, computer equipment and storage medium

Technical Field

The present application relates to the field of fault diagnosis technologies, and in particular, to a method and apparatus for locating an anomaly sensor, a computer device, and a storage medium.

Background

With the development of intelligence, the sensor plays an increasingly important role, taking an air conditioning system as an example, the measurement signal of the water chilling unit sensor is the basis of a control and monitoring system and is also the basis of energy efficiency analysis and fault diagnosis. However, in general, the sensor often has measurement deviation or drift after long-term use, and if the data provided by the sensor is unreliable, decision deviation of a control strategy may be caused, so that energy consumption of the system is increased or environmental comfort is reduced, and even the system is operated under unsafe working conditions to cause shutdown or damage. With the increase of the system scale and the increase of the complexity, the sensor fault diagnosis by the manual means is not applicable any more, so that it is necessary to introduce the on-line fault diagnosis in the control or monitoring system and output the fault information to the operation and maintenance personnel in time.

The current method for detecting and researching sensor faults is mostly a data-driven method, wherein a sensor diagnosis method based on principal component analysis (principal component analysis, PCA) is widely researched, the method has strong sensitivity to abnormal data in the sensor and high detection efficiency, but the accuracy of positioning depends on data quality and working condition coverage range, and in addition, a certain misjudgment rate exists when positioning particularly which sensor is abnormal.

Disclosure of Invention

The application aims to at least solve one of the technical defects, and particularly solves the problem that the judgment and positioning accuracy of an abnormal sensor in the prior art is not high.

In a first aspect, the present application provides a method for positioning an anomaly sensor, including:

acquiring first operation parameters of a plurality of sensors in a tested system at different moments;

grouping the plurality of sensors according to the association relationship among the plurality of sensors;

determining a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to first operation parameters of each sensor in the same group at different moments; the first comprehensive factors are obtained based on the first operation parameters of all the sensors in the same group, and the second comprehensive factors are obtained based on the first operation parameters of the two sensors in the same group;

obtaining second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors;

determining the group of sensors as an abnormal sensor group under the condition that the average value of the change rate of the second operation parameters of the sensors exceeds a corresponding threshold value;

an anomaly sensor is determined from each of the sensors in the anomaly sensor group based on a correlation between the first and second syndromes of the anomaly sensor group.

In one embodiment, the system to be tested is a chiller, and the plurality of sensors includes a chilled water inlet temperature sensor, a chilled water outlet temperature sensor, an evaporation temperature sensor, a chilled water inlet temperature sensor, a chilled water outlet temperature sensor, and a condensation temperature sensor; grouping the plurality of sensors according to an association relationship between the plurality of sensors, comprising:

the chilled water inlet temperature sensor, the chilled water outlet temperature sensor and the evaporation temperature sensor which have association relations are divided into a first sensor group, and the cooling water inlet temperature sensor, the cooling water outlet temperature sensor and the condensation temperature sensor which have association relations are divided into a second sensor group.

In one embodiment, the first operation parameters include temperatures detected by the sensors, and for the first sensor group, determining, according to the first operation parameters of the sensors in the same group at different moments, a first combination factor corresponding to each moment and two or more second combination factors includes:

according to temperatures detected by a chilled water inlet temperature sensor, a chilled water outlet temperature sensor and an evaporation temperature sensor, calculating a first logarithmic average temperature difference, and taking the first logarithmic average temperature difference as a first comprehensive factor;

And obtaining a first temperature difference according to the difference between the temperatures detected by the chilled water inlet temperature sensor and the chilled water outlet temperature sensor, obtaining a second temperature difference according to the difference between the temperatures detected by the chilled water outlet temperature sensor and the evaporation temperature sensor, and taking the first temperature difference and the second temperature difference as a second comprehensive factor.

In one embodiment, if the anomaly sensor group is a first sensor group, determining an anomaly sensor from each sensor in the anomaly sensor group according to a correlation between a first complex factor and each second complex factor of the anomaly sensor group, includes:

respectively calculating correlation coefficients of the first temperature difference, the second temperature difference and the first logarithmic average temperature difference;

if the correlation coefficient corresponding to the first temperature difference is smaller than the first threshold value but larger than zero, and the correlation coefficient corresponding to the second temperature difference is larger than the second threshold value, determining that the abnormal sensor is an evaporation temperature sensor;

if the correlation coefficient corresponding to the first temperature difference is smaller than zero and the correlation coefficient corresponding to the second temperature difference is larger than a second threshold value, determining that the abnormal sensor is a chilled water outlet temperature sensor;

if the correlation coefficient corresponding to the first temperature difference is larger than a first threshold value and the correlation coefficient corresponding to the second temperature difference is smaller than a second threshold value, determining that the abnormal sensor is a chilled water inlet temperature sensor.

In one embodiment, the first operation parameters include temperatures detected by the sensors, and for the second sensor group, determining, according to the first operation parameters of the sensors in the same group at different moments, a first combination factor corresponding to each moment and two or more second combination factors includes:

calculating a second logarithmic average temperature difference according to the temperatures detected by the cooling water inlet temperature sensor, the cooling water outlet temperature sensor and the condensation temperature sensor, and taking the second logarithmic average temperature difference as a first comprehensive factor;

and obtaining a third temperature difference according to the difference between the temperatures detected by the cooling water outlet temperature sensor and the cooling water inlet temperature sensor, obtaining a fourth temperature difference according to the difference between the temperatures detected by the condensing temperature sensor and the cooling water outlet temperature sensor, and taking the third temperature difference and the fourth temperature difference as a second comprehensive factor.

In one embodiment, if the anomaly sensor group is a second sensor group, determining the anomaly sensor from the sensors in the anomaly sensor group according to the correlation between the first complex factor and each second complex factor of the anomaly sensor group includes:

respectively calculating correlation coefficients of the third temperature difference, the fourth temperature difference and the second logarithmic average temperature difference;

If the correlation coefficient corresponding to the third temperature difference is smaller than the third threshold value but larger than zero and the correlation coefficient corresponding to the fourth temperature difference is larger than the fourth threshold value, determining that the abnormal sensor is a condensation temperature sensor;

if the correlation coefficient corresponding to the third temperature difference is smaller than zero and the correlation coefficient corresponding to the fourth temperature difference is larger than a fourth threshold value, determining that the abnormal sensor is a cooling water outlet temperature sensor;

if the correlation coefficient corresponding to the third temperature difference is larger than the third threshold value and the correlation coefficient corresponding to the fourth temperature difference is smaller than the fourth threshold value, determining that the abnormal sensor is a cooling water inlet temperature sensor.

In one embodiment, the correlation coefficient comprises a pearson correlation coefficient.

In one embodiment, obtaining the second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors includes:

and obtaining second operation parameters corresponding to the second comprehensive factors according to the preset exponential power of the quotient of the first comprehensive factors and the second comprehensive factors.

In one embodiment, acquiring first operating parameters of a plurality of sensors in a system under test at different moments includes:

after the tested system is started for a first preset time, continuously acquiring detection results output by a plurality of sensors;

And reserving the detection result with the change rate smaller than a fifth threshold value in the detection results as a first operation parameter.

In a second aspect, the present application provides a positioning device for an anomaly sensor, including:

the first operation parameter acquisition module is used for acquiring first operation parameters of a plurality of sensors in the tested system at different moments;

the grouping module is used for grouping the plurality of sensors according to the association relation among the plurality of sensors;

the comprehensive factor determining module is used for determining a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to first operation parameters of each sensor in the same group at different moments; the first comprehensive factors are obtained based on the first operation parameters of all the sensors in the same group, and the second comprehensive factors are obtained based on the first operation parameters of the two sensors in the same group;

the second operation parameter acquisition module is used for acquiring second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors;

the coarse positioning module is used for determining that the group of sensors are abnormal sensor groups under the condition that the average value of the change rate of the second operation parameters of the sensors exceeds a corresponding threshold value;

And the fine positioning module is used for determining the abnormal sensor from the sensors in the abnormal sensor group according to the correlation between the first comprehensive factors and the second comprehensive factors of the abnormal sensor group.

In a third aspect, the present application provides a computer device comprising one or more processors and a memory having stored therein computer readable instructions which, when executed by the one or more processors, perform the steps of the method for locating an anomaly sensor in any of the embodiments described above.

In a fourth aspect, the present application provides a storage medium having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the method for locating an anomaly sensor in any of the embodiments described above.

From the above technical solutions, the embodiment of the present application has the following advantages:

based on any of the above embodiments, first operation parameters of each sensor in the system under test at different moments are collected, and then the plurality of sensors are grouped according to association relations among the plurality of sensors. And calculating a first comprehensive factor and more than two second comprehensive factors of each group of sensors at different moments by using the first operation parameters, and calculating second operation parameters corresponding to each second comprehensive factor according to the first comprehensive factors and each second comprehensive factor. Due to the relation between the first and second integrated factors and the sensors and the definition of the second operation parameters, when the sensor is abnormal, the second operation parameters of the sensor group where the sensor is positioned change from stable to fluctuation. An abnormal sensor group including an abnormal sensor may be initially determined from the sensor group based on the rate of change of the second operating parameter. And finally, further locking the abnormal sensor from the abnormal sensor group by analyzing the correlation between the first comprehensive factors and the second comprehensive factors of the abnormal sensor group. The method can effectively position the abnormal sensor, complete the fault detection of the sensor on line, get rid of the dependence on data and greatly improve the abnormal judgment and the positioning precision of the sensor.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.

FIG. 1 is a flow chart of a method for locating an anomaly sensor according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a cold water unit according to an embodiment of the present application;

FIG. 3 is a schematic diagram showing the correlation of the first temperature difference, the second temperature difference and the first logarithmic average temperature difference when the first sensor group is normal;

FIG. 4 is a schematic diagram showing the correlation of the first temperature difference and the first logarithmic average temperature difference when the first sensor group introduces an anomaly in the chilled water outlet temperature sensor;

FIG. 5 is a schematic diagram showing the correlation between the second temperature difference and the first logarithmic average temperature difference when the first sensor group introduces an anomaly in the chilled water outlet temperature sensor;

FIG. 6 is a schematic diagram of a variation of a second operating parameter when the first sensor set is normal;

FIG. 7 is a schematic diagram showing a change of a second operating parameter when a fault is introduced in a first sensor group according to an embodiment of the present application;

FIG. 8 is a schematic block diagram of a positioning device of an anomaly sensor according to an embodiment of the present application;

fig. 9 is an internal structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

Referring to fig. 1, the present application provides a method for positioning an anomaly sensor, which includes steps S102 to S112.

S102, acquiring first operation parameters of a plurality of sensors in a tested system at different moments.

It is understood that the system under test is a system that operates based on detection data of a plurality of sensors, and the first operation parameter is a parameter obtained based on detection results of the respective sensors. Taking a chiller with an air conditioner as an example of the system under test, referring to fig. 2, the chiller may include four main components, namely a condenser 202, an evaporator 204, a compressor 206, and an expansion device 208, which are in fluid communication via pipes (represented by lines in fig. 2) to achieve a chiller cooling and heating effect. Specifically, expansion device 208 is in fluid communication with condenser 202 and evaporator 204 via piping, and compressor 206 is also in fluid communication with condenser 202 and evaporator 204 via piping. The condenser 202 may receive cooling water from, for example, a cooling tower (not shown) through a pipe, and heat-exchange the cooling water, and then, flow the heat-exchanged cooling water out through the pipe. The evaporator 204 can receive the chilled water through a pipeline and exchange heat with the chilled water, and then make the chilled water subjected to heat exchange pass through the pipeline And (5) flowing out. To enable control monitoring of the chiller, the chiller also includes a plurality of sensors, represented by black dots as in FIG. 2, which may include sensors for measuring chilled water inlet temperature T ₁ Is used for measuring the chilled water outlet temperature T ₂ Chilled water outlet temperature sensor for measuring evaporating temperature T ₅ Is used for measuring the inlet water temperature T of cooling water ₂ Is used for measuring the temperature T of cooling water outlet ₄ Is used for measuring condensation temperature T ₆ Is provided.

It should be noted that the evaporating temperature sensor and the condensing temperature sensor may be pressure sensors, and the detected pressure values of the evaporating pressure sensor and the condensing pressure sensor may be converted into evaporating temperature and condensing temperature respectively by using a pressure-temperature conversion table or a software fitting method. The evaporation temperature and the condensation temperature can also be measured using conventional temperature sensors.

In the system shown in fig. 2 described above, the first operating parameter may include a temperature obtained based on the detection results of the respective sensors. During the working process of the water chilling unit of the air conditioner, the sensor may be abnormal, the abnormality can be reflected in the first operation parameters, and the abnormal sensor can be locked by analyzing the first operation parameters at different moments.

S104, grouping the plurality of sensors according to the association relation among the plurality of sensors.

It should be understood that, the association relationship herein refers to the association between the physical quantities detected by the sensors, and the water chiller of fig. 2 is continuously taken as an example, the water chiller uses the evaporator 204 to exchange heat between the chilled water entering the evaporator 204 and the refrigerant, the refrigerant absorbs the heat load in the water, so that the water is cooled to generate cold water, then the heat is brought to the condenser 202 by the action of the compressor 206, the heat is exchanged between the refrigerant and the entering cooling water in the condenser 202, and the cooling water absorbs the heat and then brings the heat out through the water pipe. As shown in fig. 2, in the refrigeration cycle, at the beginning, the low-temperature low-pressure refrigerant gas after the evaporation refrigeration is sucked in by the compressor 206, and then compressed into the high-temperature high-pressure gas and sent to the condenser. The high-temperature high-pressure gas is cooled by a condenser and then condensed into high-temperature high-pressure liquid. The high temperature and high pressure liquid flows into the expansion device 208 and is throttled by the expansion device 208 to form a low temperature and low pressure two-phase refrigerant, which flows into the evaporator 204 and is used for absorbing heat of chilled water in the evaporator 204 to reduce the temperature of the water. The evaporated refrigerant is again sucked back into the compressor 206 and then the next refrigeration cycle is repeated.

Therefore, when the chilled water exchanges energy in the evaporator, the chilled water inlet temperature, the chilled water outlet temperature and the evaporation temperature are a plurality of physical quantities which are related by taking the working state of the evaporator as a core, and the chilled water inlet temperature sensor, the chilled water outlet temperature sensor and the evaporation temperature sensor have a related relationship. Similarly, when the cooling water exchanges energy in the condenser, the inlet water temperature, the outlet water temperature and the condensation temperature of the cooling water are a plurality of physical quantities which are related by taking the working state of the condenser as a core, and then the inlet water temperature sensor, the outlet water temperature sensor and the condensation temperature sensor of the cooling water have a related relationship. The chilled water inlet temperature sensor, the chilled water outlet temperature sensor and the evaporating temperature sensor which have the association relation can be divided into a first sensor group, and the cooling water inlet temperature sensor, the cooling water outlet temperature sensor and the condensing temperature sensor which have the association relation are divided into a second sensor group.

S106, determining a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to the first operation parameters of each sensor in the same group at different moments. The first integrated factor is based on the first operating parameters of all sensors in the same group, and the second integrated factor is based on the first operating parameters of both sensors in the same group.

It will be appreciated that, based on the first operating parameters of the sensors of the same group at each instant, a first combination factor and two or more second combination factors for the sensors of the group at that instant may be obtained. Because the first comprehensive factors are comprehensively calculated by the first operation parameters of each sensor in the same group, any sensor in the group can be influenced by the failure of the sensor. The second comprehensive factor is only calculated by the first operation parameters of two sensors, and only when one of the two sensors corresponding to the second comprehensive factor fails, the second comprehensive factor is influenced, and the second comprehensive factor which is irrelevant to the failed sensor is unchanged. Locking the anomaly sensor may be aided by characteristics of the first and second syndromes.

S108, obtaining second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors.

It will be appreciated that the second operating parameter is the result of substituting the first and second synthesis factors into a predetermined functional expression. When all the sensors in the same group are normal, the second operation parameters are kept stable, and when the sensors are abnormal, the abnormal operation parameters are reflected on the first comprehensive factors and the corresponding second comprehensive factors, so that the second operation parameters calculated by the first comprehensive factors and the second comprehensive factors are fluctuated.

S110, determining the group of sensors as an abnormal sensor group when the average value of the change rate of the second operation parameters of the sensors exceeds a corresponding threshold value.

The second operation parameters are in one-to-one correspondence with the acquisition time of each first operation parameter, and the change rate of the second operation parameters can be calculated according to the relation between the values of the second operation parameters at different time and time. Based on the explanation in step S108, when there is an abnormality in the sensor, the second operating parameters corresponding to the sensor group will fluctuate to different degrees. Therefore, a corresponding threshold value is set for the change rate of the second operation parameters of the sensors, and when the average value of the change rates of all the second operation parameters of the sensors exceeds the corresponding threshold value, it can be determined that the abnormal sensors exist in the group of sensors, and the group of sensors are taken as the abnormal sensor group. Specifically, it is assumed that a group of sensor groups includes two second operating parameters a and B, the rates of change corresponding to the a and B parameters at respective times are calculated, and an average value C of a plurality of rates of change corresponding to the a parameter and an average value D of a plurality of rates of change corresponding to the B parameter are calculated, respectively. And when C is larger than the corresponding threshold E and D is larger than the corresponding threshold F, judging that the sensor group is an abnormal sensor group.

S112, determining an abnormal sensor from the sensors in the abnormal sensor group according to the correlation between the first comprehensive factors and the second comprehensive factors of the abnormal sensor group.

It will be appreciated that expressing the first synthesis factor as a functional expression may be:wherein, the method comprises the steps of, wherein,y ₁ as a first combination of factors, the first combination of factors,f ₁ () To calculate the relation of the first synthesis factor,x ₁ ，x _2... x _n respectively represent and sensor groupsnAnd a first operating parameter corresponding to each sensor. The functional expression of the second synthesis factor can beWherein, the method comprises the steps of, wherein,y ₂ as a second combination of factors, the first combination,f ₂ () In order to calculate the relation of the second synthesis factor,aandbis smaller thannPositive integer of x _a And x _b Respectively represent and the firstiTwo first operating parameters associated with the second complex factor. Therefore, when all the sensors in the group of sensors are normal, the first comprehensive factors are calculated by integrating the first operation parameters of all the sensors, the second comprehensive factors are calculated by integrating the first operation parameters of only part of the sensors, the first comprehensive factors can reflect the conditions of the second comprehensive factors, and high correlation is kept between the first comprehensive factors and each second comprehensive factor.

However, whichever sensor is abnormal has an effect on the first complex factor, but the abnormal sensor has an effect on only the second complex factor associated with itself. The influence of the anomaly sensor on the first and the second integration factors can be represented by the values and signs of the correlation coefficients, i.e. the presence of the anomaly sensor will result in a change in the correlation of the second integration factor associated with the anomaly sensor with the first integration factor. And, because each second comprehensive factor is only relevant to two sensors, after finding the second comprehensive factor corresponding to the change of the correlation, the range of the abnormal sensor can be reduced to two sensors relevant to the second comprehensive factor. By utilizing this characteristic, if there are two or more correlations that change, the same one of the two sensors that are each locked and have a possibility of abnormality is an abnormality sensor. The characteristic that the two sensors related to the second comprehensive factors corresponding to the unchanged correlation do not belong to the abnormal sensor can be combined, the abnormal sensor can be further found out after the two sensors are further excluded from the reduced range. And the influence of each sensor on the change condition of the correlation can be analyzed, and the sensor with the influence matched with the actual change condition is selected as the abnormal sensor by combining the actual change condition of the second comprehensive factor corresponding to the change of the correlation. For example, when the relational expression of the second comprehensive factors is set, the influence of the two first operation parameters in the second comprehensive factors on the correlation parameters is set to be different in combination with the calculation formula of the correlation parameters. The analysis modes can be used singly or in combination, and can be selected according to actual conditions.

Based on the positioning method of the abnormal sensor in the embodiment, first operation parameters of each sensor in the tested system at different moments are collected, and then the sensors are grouped according to the association relations among the sensors. And calculating a first comprehensive factor and more than two second comprehensive factors of each group of sensors at different moments by using the first operation parameters, and calculating second operation parameters corresponding to each second comprehensive factor according to the first comprehensive factors and each second comprehensive factor. Due to the relation between the first and second integrated factors and the sensors and the definition of the second operation parameters, when the sensor is abnormal, the second operation parameters of the sensor group where the sensor is positioned change from stable to fluctuation. An abnormal sensor group including an abnormal sensor may be initially determined from the sensor group based on the rate of change of the second operating parameter. And finally, further locking the abnormal sensor from the abnormal sensor group by analyzing the correlation between the first comprehensive factors and the second comprehensive factors of the abnormal sensor group. The method can effectively position the abnormal sensor, complete the fault detection of the sensor on line, get rid of the dependence on data and greatly improve the abnormal judgment and the positioning precision of the sensor.

In one embodiment, the first operation parameters include temperatures detected by the sensors, and for the first sensor group, determining, according to the first operation parameters of the sensors in the same group at different moments, a first combination factor corresponding to each moment and two or more second combination factors includes:

(1) And calculating a first logarithmic average temperature difference according to the temperatures detected by the chilled water inlet temperature sensor, the chilled water outlet temperature sensor and the evaporation temperature sensor, and taking the first logarithmic average temperature difference as a first comprehensive factor.

It will be appreciated that the logarithmic mean temperature difference (Logarithmic Mean Temperature Difference, LMTD), abbreviated as LMTD, is a parameter used in heat transfer fluid systems to analyze heat exchange conditions. Which means the logarithmic average of the cold and hot side temperature differences in a double tube heat exchanger. Other parameters are set, and the larger the logarithmic average temperature difference is, the larger the heat transfer amount is. The first logarithmic average temperature difference is expressed by a functional expression as follows:

；

wherein, the liquid crystal display device comprises a liquid crystal display device,LMTD _e i.e. representing the first logarithmic mean temperature difference,T ₁ representing the temperature detected based on the chilled water inlet temperature sensor,T ₂ representing the temperature detected by the chilled water outlet water temperature sensor, T ₅ Representing the temperature detected based on the evaporation temperature sensor.

(2) And obtaining a first temperature difference according to the difference between the temperatures detected by the chilled water inlet temperature sensor and the chilled water outlet temperature sensor, obtaining a second temperature difference according to the difference between the temperatures detected by the chilled water outlet temperature sensor and the evaporation temperature sensor, and taking the first temperature difference and the second temperature difference as a second comprehensive factor.

It can be understood that the second comprehensive factors of the first sensor group in this embodiment are two, namely the first temperature difference and the second temperature difference. The first temperature difference and the second temperature difference are expressed by a functional expression:

；

；

wherein, the liquid crystal display device comprises a liquid crystal display device,representing a first temperature difference, +.>Representing a second temperature difference.

In one embodiment, if the anomaly sensor group is a first sensor group, determining an anomaly sensor from each sensor in the anomaly sensor group according to a correlation between a first complex factor and each second complex factor of the anomaly sensor group, includes:

(1) And respectively calculating correlation coefficients of the first temperature difference, the second temperature difference and the first logarithmic average temperature difference.

It is understood that the correlation coefficient may reflect the magnitude of the correlation between two variables. Since the first temperature difference, the second temperature difference, and the first logarithmic average temperature difference each comprise a plurality of data points at different times, they can be regarded as time-varying variables. And when the correlation coefficient is calculated, the correlation coefficient of the first temperature difference and the first logarithmic average temperature difference and the correlation coefficient of the second temperature difference and the first logarithmic average temperature difference are calculated respectively. The larger the absolute value of the correlation coefficient, the stronger the correlation between the two variables. And the correlation coefficient is positive, then The positive correlation between two variables is shown, whereas the negative correlation between the two variables is shown. The correlation coefficient corresponding to the first temperature difference is called ρ for convenience of description _A The correlation coefficient corresponding to the second temperature difference is called ρ _B . Referring to FIG. 3, when the sensors in the first sensor group are all normal, the first temperature difference and the first logarithmic average temperature difference, the second temperature difference and the first logarithmic average temperature difference are linearly and positively correlated, i.e., ρ _A Will be greater than the first threshold, ρ _B Will be greater than the second threshold.

(2) And if the correlation coefficient corresponding to the first temperature difference is smaller than the first threshold value but larger than zero and the correlation coefficient corresponding to the second temperature difference is larger than the second threshold value, determining that the abnormal sensor is an evaporation temperature sensor.

It can be appreciated that when ρ _A Below the first threshold but above zero, it is indicative of the first temperature difference being positively correlated with the first logarithmic mean temperature difference, but the correlation has decreased, ρ _B A value greater than the second threshold represents a significant positive correlation of the second temperature difference with the first logarithmic average temperature difference. Description of the anomaly sensor pair ρ when an anomaly sensor is present in the first sensor group _A Has a larger influence on ρ _B The effect of (2) is small, meaning that the effect is caused by the second temperature difference related sensor rather than the first temperature difference related sensor, and the abnormal sensor can be identified as an evaporating temperature sensor by the elimination method.

(3) If the correlation coefficient corresponding to the first temperature difference is smaller than zero and the correlation coefficient corresponding to the second temperature difference is larger than a second threshold value, determining that the abnormal sensor is a chilled water outlet temperature sensor.

It can be appreciated that when ρ _A Less than zero, the first temperature difference and the first logarithmic average temperature difference are changed from positive correlation to negative correlation, and ρ _B A value greater than the second threshold represents a significant positive correlation of the second temperature difference with the first logarithmic average temperature difference. Indicating that when an anomaly sensor is present in the first sensor group, the fluctuation of the first logarithmic mean temperature difference is caused by the second temperature difference-related sensor, and the sensor can change ρ _A Is a symbol of (c). The expression combining the first temperature difference and the second temperature difference can be knownThe water outlet temperature of the frozen water is related to the two temperature differences, and the signs are different, when the water outlet temperature of the frozen water is taken as an abnormal source, the signs of the correlation of the water outlet temperature of the frozen water and the first temperature difference and the correlation of the water outlet temperature of the frozen water and the first logarithmic average temperature difference are opposite, and ρ is _A Is calculated based on the first temperature difference and the first logarithmic average temperature difference, resulting in ρ _A Therefore, when the correlation coefficient corresponding to the first temperature difference is changed from positive correlation to negative correlation, the abnormal sensor can be identified as the chilled water outlet water temperature sensor. Referring to fig. 4 and 5, after the disturbance is introduced into the chilled water outlet temperature sensor, the first temperature difference and the first logarithmic average temperature difference become a negative correlation, and the second temperature difference and the first logarithmic average temperature difference still maintain good linear positive correlation.

(4) If the correlation coefficient corresponding to the first temperature difference is larger than a first threshold value and the correlation coefficient corresponding to the second temperature difference is smaller than a second threshold value, determining that the abnormal sensor is a chilled water inlet temperature sensor.

It can be appreciated that when ρ _A Above the first threshold, it is indicative of the first temperature difference having a significant positive correlation with the first logarithmic mean temperature difference, ρ _B A value less than the second threshold represents a weaker correlation of the second temperature difference with the first logarithmic mean temperature difference. Description of the anomaly sensor pair ρ when an anomaly sensor is present in the first sensor group _B Is of greater influence on ρ _A The influence of the sensor is small, namely, the influence is caused by a sensor related to the first temperature difference and a sensor related to the second temperature difference, and the abnormal sensor can be identified as a chilled water inlet temperature sensor by utilizing the elimination method.

In one embodiment, the first operation parameters include temperatures detected by the sensors, and for the second sensor group, determining, according to the first operation parameters of the sensors in the same group at different moments, a first combination factor corresponding to each moment and two or more second combination factors includes:

(1) And calculating a second logarithmic average temperature difference according to the temperatures detected by the cooling water inlet temperature sensor, the cooling water outlet temperature sensor and the condensing temperature sensor, and taking the second logarithmic average temperature difference as a first comprehensive factor.

The definition of the logarithmic mean temperature difference can be referred to above, and the function expression is used to express the second logarithmic mean temperature difference as follows:

；

wherein, the liquid crystal display device comprises a liquid crystal display device,LMTD _c i.e. representing the second logarithmic mean temperature difference,T ₃ representing the temperature detected based on the cooling water inlet temperature sensor,T ₄ representing the temperature detected by the outlet water temperature sensor based on the cooling water,T ₆ representing the temperature detected based on the condensing temperature sensor.

(2) And obtaining a third temperature difference according to the difference between the temperatures detected by the cooling water outlet temperature sensor and the cooling water inlet temperature sensor, obtaining a fourth temperature difference according to the difference between the temperatures detected by the condensing temperature sensor and the cooling water outlet temperature sensor, and taking the third temperature difference and the fourth temperature difference as a second comprehensive factor.

It can be understood that the second comprehensive factors of the second sensor group in this embodiment are two, namely the third temperature difference and the fourth temperature difference. The third temperature difference and the fourth temperature difference are expressed by functional expressions:

；

；

wherein, the liquid crystal display device comprises a liquid crystal display device,representing a third temperature difference, +.>Representing a fourth temperature difference.

In one embodiment, if the anomaly sensor group is a second sensor group, determining the anomaly sensor from the sensors in the anomaly sensor group according to the correlation between the first complex factor and each second complex factor of the anomaly sensor group includes:

(1) And respectively calculating correlation coefficients of the third temperature difference, the fourth temperature difference and the second logarithmic average temperature difference.

It is understood that the correlation coefficient may reflect the magnitude of the correlation between two variables. Since the third temperature difference, the fourth temperature difference, and the second logarithmic average temperature difference each comprise a plurality of data points at different times, they can be regarded as time-varying variables. And when the correlation coefficient is calculated, respectively calculating the correlation coefficient of the third temperature difference and the second logarithmic average temperature difference and the correlation coefficient of the fourth temperature difference and the second logarithmic average temperature difference. The larger the absolute value of the correlation coefficient, the stronger the correlation between the two variables. And the positive correlation coefficient represents the positive correlation between the two variables, and the negative correlation between the two variables. The correlation coefficient corresponding to the third temperature difference is called ρ for convenience of description _C The correlation coefficient corresponding to the fourth temperature difference is called ρ _D . The pattern is similar to that of fig. 3 and is therefore not shown. When the sensors in the second sensor group are all normal, the third temperature difference and the second logarithmic average temperature difference, the fourth temperature difference and the second logarithmic average temperature difference are in linear positive correlation, namely ρ _C Will be greater than a third threshold, ρ _D Will be greater than the fourth threshold.

(2) And if the correlation coefficient corresponding to the third temperature difference is smaller than the third threshold value but larger than zero and the correlation coefficient corresponding to the fourth temperature difference is larger than the fourth threshold value, determining that the abnormal sensor is a condensation temperature sensor.

It can be appreciated that when ρ _C Below the third threshold but above zero, this represents that the third temperature difference is positively correlated with the second logarithmic mean temperature difference, but the correlation has decreased, ρ _D A value greater than the fourth threshold represents a significant positive correlation of the fourth temperature difference with the second logarithmic average temperature difference. Description of the anomaly sensor pair ρ when an anomaly sensor is present in the second sensor group _C Has a larger influence on ρ _D The influence of the sensor is small, that is, it is represented that the influence is caused by the sensor related to the fourth temperature difference rather than the sensor related to the third temperature difference, and the abnormal sensor can be recognized as the condensing temperature sensor by the elimination method.

(3) If the correlation coefficient corresponding to the third temperature difference is smaller than zero and the correlation coefficient corresponding to the fourth temperature difference is larger than a fourth threshold value, determining that the abnormal sensor is a cooling water outlet temperature sensor.

It can be appreciated that when ρ _C Less than zero, the third temperature difference and the second logarithmic average temperature difference are changed from positive correlation to negative correlation, and ρ _D A value greater than the fourth threshold represents a significant positive correlation of the fourth temperature difference with the second logarithmic average temperature difference. Indicating that the fluctuation of the second logarithmic mean temperature difference is caused by the fourth temperature difference-related sensor when an abnormal sensor is present in the second sensor group, and the sensor can change ρ _C Is a symbol of (c). As can be seen from the expression combining the third temperature difference and the fourth temperature difference, the cooling water outlet temperature is related to both the temperature differences, and the signs are different, when the cooling water outlet temperature is taken as an abnormal source, the signs of the correlation of the cooling water outlet temperature and the third temperature difference and the correlation of the cooling water outlet temperature and the second logarithmic average temperature difference are opposite, and ρ is _C Is calculated based on the third temperature difference and the second logarithmic average temperature difference, resulting in ρ _C Therefore, when the correlation coefficient corresponding to the third temperature difference is changed from positive correlation to negative correlation, the abnormal sensor can be identified as the cooling water outlet temperature sensor.

(4) If the correlation coefficient corresponding to the third temperature difference is larger than the third threshold value and the correlation coefficient corresponding to the fourth temperature difference is smaller than the fourth threshold value, determining that the abnormal sensor is a cooling water inlet temperature sensor.

It can be appreciated that when ρ _C Above the third threshold, it is indicative of the third temperature difference having a significant positive correlation with the second logarithmic mean temperature difference, ρ _D A value less than the fourth threshold represents a weaker correlation of the fourth temperature difference with the second logarithmic mean temperature difference. Description of the anomaly sensor pair ρ when an anomaly sensor is present in the second sensor group _D Is greater in influence of (a)And p is opposite to _C The influence of the third temperature difference is small, namely, the influence is caused by a sensor related to the third temperature difference rather than a sensor related to the fourth temperature difference, and the abnormal sensor can be identified as a cooling water inlet temperature sensor by utilizing the elimination method.

In one embodiment, the correlation coefficient comprises a pearson correlation coefficient. The pearson correlation coefficient is a statistic for measuring the linear correlation degree between two variables, the value range is-1 to 1, and when the coefficient is close to 1, the two variables are indicated to be in positive correlation, namely, one variable is increased, and the other variable is also increased. When the coefficient is close to-1, the two variables are indicated to be in a negative correlation relationship, namely one variable is increased, and the other variable is decreased; when the coefficient approaches 0, it is stated that there is no linear relationship between the two variables. The calculation expression of the pearson correlation coefficient may be:

；

In the method, in the process of the invention,for two variablesXAndYis a covariance of (2); />、/>Respectively isXAndYstandard deviation of (2). Will beXAndYsubstituting the first comprehensive factors and the second comprehensive factors respectively, and calculating the pearson correlation coefficients of the first comprehensive factors and the second comprehensive factors.

In one embodiment, obtaining the second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors includes: and obtaining second operation parameters corresponding to the second comprehensive factors according to the preset exponential power of the quotient of the first comprehensive factors and the second comprehensive factors.

Specifically, the expression of the second operation parameter calculated from the first temperature difference and the first logarithmic average temperature difference may be:

；

wherein, the liquid crystal display device comprises a liquid crystal display device,ConstantAfor a second operating parameter corresponding to the first temperature difference,αto the power of a preset index,

the expression of the second operating parameter calculated from the second temperature difference and the first logarithmic average temperature difference may be:

；

wherein, the liquid crystal display device comprises a liquid crystal display device,ConstantBand the second operation parameter is corresponding to the second temperature difference.αFitting can be performed according to the experimental results, please refer to fig. 6 and 7, and a suitable choice is madeαIt is ensured that the second operating parameter remains stable when the sensor is normal, while a significant fluctuation occurs when an abnormality occurs in the sensor.

The expression of the second operating parameter calculated from the third temperature difference and the second logarithmic average temperature difference may be:

；

wherein, the liquid crystal display device comprises a liquid crystal display device,ConstantCand the second operation parameter corresponding to the third temperature difference.

The expression of the second operating parameter calculated from the fourth temperature difference and the second logarithmic average temperature difference may be:

；

wherein, the liquid crystal display device comprises a liquid crystal display device,ConstantDand the second operation parameter corresponding to the fourth temperature difference.

In one embodiment, acquiring first operating parameters of a plurality of sensors in a system under test at different moments includes:

(1) After the tested system is started for a first preset time, detection results output by the plurality of sensors are continuously obtained.

It can be understood that after the tested system is started for a first preset time, the working state of the sensor is stabilized, and the detection results output by a plurality of sensors in the tested system are obtained. Taking the tested system in fig. 2 as an example, the temperatures detected by the chilled water inlet temperature sensor, the chilled water outlet temperature sensor, the evaporating temperature sensor, the cooling water inlet temperature sensor, the cooling water outlet temperature sensor and the condensing temperature sensor are obtained.

(2) And reserving the detection result with the change rate smaller than a fifth threshold value in the detection results as a first operation parameter.

In the process of continuously acquiring the detection result of the sensor, the data at certain moments may be lost due to the problems of data transmission and the like, so that erroneous judgment on the fault state of the sensor may occur. Therefore, after the detection result is obtained, the detection result is filtered first, and the detection result truly reflecting the sensor state is retained, that is, only the portion in which the change rate is smaller than the fifth threshold value is retained.

The application provides a positioning device of an abnormal sensor, referring to fig. 8, comprising a first operation parameter acquisition module 810, a grouping module 820, a comprehensive factor determination module 830, a second operation parameter acquisition module 840, a coarse positioning module 850 and a fine positioning module 860.

The first operation parameter obtaining module 810 is configured to obtain first operation parameters of a plurality of sensors in a tested system at different moments.

The grouping module 820 is configured to group the plurality of sensors according to an association relationship between the plurality of sensors.

The comprehensive factor determining module 830 is configured to determine a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to first operation parameters of each sensor in the same group at different moments. The first integrated factor is based on the first operating parameters of all sensors in the same group, and the second integrated factor is based on the first operating parameters of both sensors in the same group.

The second operation parameter obtaining module 840 is configured to obtain second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors.

The coarse positioning module 850 is configured to determine that the set of sensors is an abnormal sensor set if a rate of change of a second operating parameter of the sensors exceeds a corresponding threshold.

The fine positioning module 860 is configured to determine an anomaly sensor from among the sensors in the anomaly sensor set based on a correlation between the first and second syndromes of the anomaly sensor set.

For specific limitations on the positioning means of the anomaly sensor, reference may be made to the above limitations on the positioning method of the anomaly sensor, and no further description is given here. The above-described respective modules in the positioning device of the abnormality sensor may be implemented in whole or in part by software, hardware, or a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules. It should be noted that, in the embodiment of the present application, the division of the modules is schematic, which is merely a logic function division, and other division manners may be implemented in actual implementation.

The present application provides a computer device comprising one or more processors and a memory having stored therein computer readable instructions which, when executed by the one or more processors, perform the steps of the method for locating an anomaly sensor of any of the embodiments described above.

Schematically, as shown in fig. 9, fig. 9 is a schematic internal structure of a computer device provided in an embodiment of the present application, where the computer device 900 may be configured in an unmanned vehicle. Referring to FIG. 9, a computer device 900 includes a processing component 902 that further includes one or more processors, and memory resources represented by memory 901, for storing instructions, such as applications, executable by the processing component 902. The application program stored in the memory 901 may include one or more modules each corresponding to a set of instructions. Further, the processing component 902 is configured to execute instructions to perform the steps of the anomaly sensor locating method or the control arbitration method of any of the embodiments described above.

The computer device 900 may also include a power component 903 configured to perform power management of the computer device 900, a wired or wireless network interface 904 configured to connect the computer device 900 to a network, and an input output (I/O) interface 905. The computer device 900 may operate based on an operating system stored in memory 901, such as Windows Server TM, mac OS XTM, unix, linux, free BSDTM, or the like.

It will be appreciated by persons skilled in the art that the architecture shown in fig. 9 is merely a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

The present application provides a storage medium having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the method for locating an anomaly sensor in any of the embodiments described above.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

In the present specification, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and may be combined according to needs, and the same similar parts may be referred to each other.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. A method of locating an anomaly sensor, comprising:

acquiring first operation parameters of a plurality of sensors in a tested system at different moments; the system to be tested is a water chiller, the plurality of sensors comprise a chilled water inlet temperature sensor, a chilled water outlet temperature sensor, an evaporation temperature sensor, a cooling water inlet temperature sensor, a cooling water outlet temperature sensor and a condensation temperature sensor, and the first operation parameters comprise the temperature detected by each sensor;

Grouping the plurality of sensors according to the association relationship among the plurality of sensors; the grouping the plurality of sensors according to the association relationship between the plurality of sensors includes: dividing the chilled water inlet temperature sensor, the chilled water outlet temperature sensor and the evaporation temperature sensor which have association into a first sensor group, and dividing the cooling water inlet temperature sensor, the cooling water outlet temperature sensor and the condensation temperature sensor which have association into a second sensor group;

determining a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to the first operation parameters of each sensor in the same group at different moments; the first comprehensive factors are obtained based on the first operation parameters of all the sensors in the same group, and the second comprehensive factors are obtained based on the first operation parameters of two sensors in the same group; for the first sensor group, determining a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to the first operation parameters of each sensor in the same group at different moments, including: calculating a first logarithmic average temperature difference according to the temperatures detected by the chilled water inlet temperature sensor, the chilled water outlet temperature sensor and the evaporation temperature sensor, and taking the first logarithmic average temperature difference as the first comprehensive factor; obtaining a first temperature difference according to the difference between the temperatures detected by the chilled water inlet temperature sensor and the chilled water outlet temperature sensor, obtaining a second temperature difference according to the difference between the temperatures detected by the chilled water outlet temperature sensor and the evaporation temperature sensor, and taking the first temperature difference and the second temperature difference as the second comprehensive factors;

Obtaining second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors;

determining that the set of sensors is an abnormal sensor set if an average of rates of change of the second operating parameters of the sensors exceeds a corresponding threshold;

an anomaly sensor is determined from each of the sensors in the anomaly sensor group based on a correlation between the first and second syndromes of the anomaly sensor group.

2. The positioning method according to claim 1, wherein if the anomaly sensor group is the first sensor group, the determining an anomaly sensor from each sensor in the anomaly sensor group based on a correlation between the first and second integrated factors of the anomaly sensor group includes:

respectively calculating correlation coefficients of the first temperature difference, the second temperature difference and the first logarithmic average temperature difference;

if the correlation coefficient corresponding to the first temperature difference is smaller than a first threshold value but larger than zero, and the correlation coefficient corresponding to the second temperature difference is larger than a second threshold value, determining that the abnormal sensor is the evaporation temperature sensor;

If the correlation coefficient corresponding to the first temperature difference is smaller than zero and the correlation coefficient corresponding to the second temperature difference is larger than the second threshold, determining that the abnormal sensor is the chilled water outlet temperature sensor;

and if the correlation coefficient corresponding to the first temperature difference is larger than the first threshold value and the correlation coefficient corresponding to the second temperature difference is smaller than the second threshold value, determining that the abnormal sensor is the chilled water inlet temperature sensor.

3. The positioning method according to claim 1, wherein the first operation parameters include temperatures detected by the sensors, and for the second sensor group, the determining, based on the first operation parameters of the sensors in the same group at different timings, a first combination factor and two or more second combination factors corresponding to the timings includes:

calculating a second logarithmic average temperature difference according to the temperatures detected by the cooling water inlet temperature sensor, the cooling water outlet temperature sensor and the condensing temperature sensor, and taking the second logarithmic average temperature difference as the first comprehensive factor;

and obtaining a third temperature difference according to the difference between the temperatures detected by the cooling water outlet temperature sensor and the cooling water inlet temperature sensor, obtaining a fourth temperature difference according to the difference between the temperatures detected by the condensing temperature sensor and the cooling water outlet temperature sensor, and taking the third temperature difference and the fourth temperature difference as the second comprehensive factors.

4. A positioning method according to claim 3, wherein if the anomaly sensor group is the second sensor group, the determining an anomaly sensor from each of the sensors in the anomaly sensor group based on a correlation between the first and second integrated factors of the anomaly sensor group comprises:

respectively calculating correlation coefficients of the third temperature difference, the fourth temperature difference and the second logarithmic average temperature difference;

if the correlation coefficient corresponding to the third temperature difference is smaller than a third threshold value but larger than zero, and the correlation coefficient corresponding to the fourth temperature difference is larger than a fourth threshold value, determining that the abnormal sensor is the condensation temperature sensor;

if the correlation coefficient corresponding to the third temperature difference is smaller than zero and the correlation coefficient corresponding to the fourth temperature difference is larger than the fourth threshold, determining that the abnormal sensor is the cooling water outlet temperature sensor;

and if the correlation coefficient corresponding to the third temperature difference is larger than the third threshold value and the correlation coefficient corresponding to the fourth temperature difference is smaller than the fourth threshold value, determining that the abnormal sensor is the cooling water inlet temperature sensor.

5. The positioning method according to claim 2 or 4, wherein the correlation coefficient comprises a pearson correlation coefficient.

6. The positioning method according to claim 2 or 4, wherein the obtaining, according to the first comprehensive factors and each of the second comprehensive factors, second operation parameters corresponding to each of the second comprehensive factors includes:

and obtaining second operation parameters corresponding to the second comprehensive factors according to the preset exponential power of the quotient of the first comprehensive factors and the second comprehensive factors.

7. The positioning method according to claim 1, wherein the acquiring the first operation parameters of the plurality of sensors in the measured system at different moments comprises:

after the tested system is started for a first preset time, continuously acquiring detection results output by the plurality of sensors;

and reserving the detection result with the change rate smaller than a fifth threshold value in the detection results as the first operation parameter.

8. A positioning device of an abnormality sensor, comprising:

the first operation parameter acquisition module is used for acquiring first operation parameters of a plurality of sensors in the tested system at different moments; the system to be tested is a water chiller, the plurality of sensors comprise a chilled water inlet temperature sensor, a chilled water outlet temperature sensor, an evaporation temperature sensor, a cooling water inlet temperature sensor, a cooling water outlet temperature sensor and a condensation temperature sensor, and the first operation parameters comprise the temperature detected by each sensor;

The grouping module is used for grouping the plurality of sensors according to the association relation among the plurality of sensors; the grouping the plurality of sensors according to the association relationship between the plurality of sensors includes: dividing the chilled water inlet temperature sensor, the chilled water outlet temperature sensor and the evaporation temperature sensor which have association into a first sensor group, and dividing the cooling water inlet temperature sensor, the cooling water outlet temperature sensor and the condensation temperature sensor which have association into a second sensor group;

the comprehensive factor determining module is used for determining a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to the first operation parameters of each sensor in the same group at different moments; the first comprehensive factors are obtained based on the first operation parameters of all the sensors in the same group, and the second comprehensive factors are obtained based on the first operation parameters of two sensors in the same group; for the first sensor group, determining a first comprehensive factor and more than two second comprehensive factors corresponding to each moment according to the first operation parameters of each sensor in the same group at different moments, including: calculating a first logarithmic average temperature difference according to the temperatures detected by the chilled water inlet temperature sensor, the chilled water outlet temperature sensor and the evaporation temperature sensor, and taking the first logarithmic average temperature difference as the first comprehensive factor; obtaining a first temperature difference according to the difference between the temperatures detected by the chilled water inlet temperature sensor and the chilled water outlet temperature sensor, obtaining a second temperature difference according to the difference between the temperatures detected by the chilled water outlet temperature sensor and the evaporation temperature sensor, and taking the first temperature difference and the second temperature difference as the second comprehensive factors;

The second operation parameter acquisition module is used for acquiring second operation parameters corresponding to the second comprehensive factors according to the first comprehensive factors and the second comprehensive factors;

the coarse positioning module is used for determining that the group of the sensors is an abnormal sensor group under the condition that the average value of the change rate of the second operation parameters of the sensors exceeds a corresponding threshold value;

and the fine positioning module is used for determining an abnormal sensor from the sensors in the abnormal sensor group according to the correlation between the first comprehensive factors and the second comprehensive factors of the abnormal sensor group.

9. A computer device comprising one or more processors and a memory having stored therein computer readable instructions which, when executed by the one or more processors, perform the steps of the method of locating an anomaly sensor as claimed in any one of claims 1 to 7.

10. A storage medium having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the method of locating an anomaly sensor as claimed in any one of claims 1 to 7.