State identification device

Abstract

A state identification device (1) causes a processor (2) to execute: processing for acquiring a plurality of physical parameters from a detector (50) for monitoring a monitoring target; processing for using a plurality of physical parameters to perform determination by a plurality of determiners (10) including at least a first determiner and a second determiner using the MT method; and processing for outputting an identification signal indicating whether or not the state of the monitoring target belongs to a single predetermined state on the basis of determination results from the plurality of determiners. The first determiner (11) transitions to terminating processing of the state identification device or to looping the processing of the first determiner, without performing processing of another determiner or the processing for outputting the identification signal. The second determiner (12) is a determiner that is transitioned after the processing of the first determiner connected in series, or a determiner that transitions to terminating the processing of the state identification device or to looping the processing of the second determiner, without performing the processing of another determiner or the processing for outputting the identification signal.

Description

Condition Identification Device

[0001] The present invention relates to a state identification device that outputs an identification signal indicating whether or not a state of an object to be monitored belongs to a single predetermined state.

[0002] Conventionally, in various technical fields, various condition identification devices are used that output an identification signal indicating whether the condition of a monitored object belongs to a predetermined condition. For example, various condition identification devices are also used in the technical field of engine-mounted devices. For example, Patent Document 1 discloses a condition identification device that outputs an identification signal indicating whether a catalyst that purifies exhaust gas emitted from an engine is in a deteriorated state. Furthermore, Patent Document 2 discloses a condition identification device that outputs an identification signal indicating whether an engine is in a misfire state. The condition identification device of Patent Document 2 identifies whether an engine is in a misfire state by performing a detailed analysis of a signal from an engine rotation speed sensor.

[0003] Furthermore, various state identification devices have been proposed that use the Mahalanobis-Taguchi method (MT method) to output an identification signal indicating whether the state of a monitored object belongs to a predetermined state. For example, Patent Document 3 discloses a state identification device that uses the MT method to output an identification signal indicating whether knocking is occurring. Also, Patent Document 4 discloses a state identification device that uses the MT method to output an identification signal indicating whether an engine is in a misfire state.

[0004] Also disclosed is a condition identification device including a plurality of judgers using the MT method. For example, Patent Document 5 discloses a device that includes a plurality of judgers using the MT method and identifies whether a processing device is in an abnormal state. The condition identification device in Patent Document 5 has three judgers using the MT method connected in series to determine three types of abnormal states in a stepwise manner.

[0005] International Publication No. 2021 / 182584 International Publication No. 2016 / 194953 Japanese Patent Application Laid-Open No. 2020-056331 Japanese Patent Application Laid-Open No. 2010-014065 Japanese Patent Application Laid-Open No. 2021-163054

[0006] In condition identification devices that do not use the MT method, such as those disclosed in Patent Documents 1 and 2, the load of computational processing is high in order to ensure high identification accuracy. Therefore, high-performance hardware resources, such as a processor with high processing power and a large-capacity memory, are required. Therefore, the degree of freedom in designing the hardware resources of the condition identification device is low. In contrast, a condition identification device that uses the MT method can reduce the load of computational processing while improving identification accuracy compared to condition identification devices that do not use the MT method. By reducing the load of computational processing, the degree of freedom in designing the hardware resources of the condition identification device can be improved. Therefore, a condition identification device that identifies the state of a monitored object using multiple determinators that use the MT method is required to ensure high identification accuracy, while making the identification process more efficient and improving the degree of freedom in designing the hardware resources.

[0007] The present invention aims to propose a state identification device that identifies the state of a monitored object using multiple determiners that use the MT method, thereby ensuring high identification accuracy while making the identification process more efficient and improving the design freedom of hardware resources.

[0008] (1) A state identification device according to one embodiment of the present invention has the following configuration: A state identification device that outputs an identification signal indicating whether or not a state of a monitored object belongs to a single predetermined state, the state identification device comprising a processor and a storage device operatively coupled to the processor, the storage device storing a program executed by the processor, the program causing the state identification device to execute the following processes: (A) acquiring a plurality of physical parameters from at least one detector that monitors the monitored object; (B) making a judgment using the acquired plurality of physical parameters with a plurality of judgers; and (C) outputting an identification signal indicating whether or not the state of the monitored object belongs to the single predetermined state based on a judgment result of at least any one of the plurality of judgers, the plurality of judgers including at least a first judger and a second judger that use the Mahalanobis-Taguchi method, the first decision unit is a decision unit that calculates a Mahalanobis distance of a first parameter set selected from the acquired plurality of physical parameters in a first unit space constructed using a first mean vector and a first variance-covariance matrix that are calculated in advance, and compares the calculated Mahalanobis distance with a first threshold value to decide whether or not a first condition is satisfied, and when the comparison result of the first decision unit either satisfies or does not satisfy the first condition, the first decision unit is shifted to terminating the processing of the state identification device or looping the processing of the first decision unit without going through either the processing of any of the plurality of decision units or the processing of outputting the identification signal; The second determiner is a determiner that calculates a Mahalanobis distance of a second parameter set selected from the acquired physical parameters in a second unit space that is different from the first unit space and is constructed using a pre-calculated second mean vector and a second variance-covariance matrix, and compares the calculated Mahalanobis distance with a second threshold value to determine whether a second condition is satisfied, and corresponds to at least one of the following determiner (i) and determiner (ii).(i) a determiner connected in series with the first determiner, and transitioned after the processing of the first determiner when the comparison result by the first determiner satisfies or does not satisfy the first condition, and (ii) a determiner that, when the comparison result satisfies or does not satisfy the second condition, ends the processing of the state identification device without transitioning to either the processing of any of the plurality of determiners or the processing of outputting the identification signal, or transitions to loop the processing of the second determiner.

[0009] A condition identification device that identifies the condition of a monitored object using multiple decision elements using the MT method has a reduced computational load compared to a condition identification device that does not use the MT method. However, calculating the Mahalanobis distance requires matrix calculations using mean vectors and variance-covariance matrices, which requires high-load computations in multidimensional data processing. These processes intensively utilize the floating-point processing unit of the processor and require frequent memory accesses and the allocation of memory space for the mean vectors and variance-covariance matrices. According to this configuration, (i) a decision element that terminates or transitions to a loop without proceeding to another decision element or to a process that outputs an identification signal is provided before two decision elements connected in series. Alternatively, or in addition to (i), (ii) a plurality of decision elements that terminate or transition to a loop without proceeding to another decision element or to a process that outputs an identification signal are provided. Here, if a decision unit that, after making a decision, terminates or transitions to a loop of the decision unit's processing without proceeding to the other decision unit and processing to output an identification signal, is (i) provided in the preceding stage of two decision units connected in series, the decision unit will terminate or transition to a loop of the decision unit's processing when a specific condition is met, thereby preventing unnecessary high-load calculation processing by a subsequent decision unit in the series-connected configuration. Also, if multiple decision units that, after making a decision, terminate or transition to a loop of the decision unit's processing without proceeding to the other decision unit and processing to output an identification signal, (ii) are provided, it is possible to flexibly respond to cases where a wide variety of conditions or complex branching is required in the processing of the state identification device, and the decision unit will terminate or transition to a loop of the decision unit's processing when a specific condition is met, thereby preventing unnecessary high-load calculation processing by the other decision units.Therefore, in either case where, after a judgment, (i) a judger that terminates or transitions to a loop of the processing of that judger without transitioning to a process of outputting the other judger and an identification signal is provided in a stage preceding two judgers connected in series, or (ii) where a plurality of judgers that terminate or transition to a loop of the processing of that judger without transitioning to a process of outputting the other judger and an identification signal are provided, unnecessary high-load calculation processing is not executed, thereby preventing waste of hardware resources (memory, CPU, I / O devices, etc.), reducing processing delays, and making the processing of the state identification device more efficient. As a result, by using the MT method, it is possible to ensure high classification accuracy, make the classification processing more efficient, and increase the design freedom of hardware resources.

[0010] (2) In addition to the configuration of (1) above, the state identification device according to one embodiment of the present invention may have the following configuration: The second parameter set includes at least some physical parameters of the first parameter set.

[0011] According to this configuration, the first and second decision devices calculate the Mahalanobis distance using at least a portion of the same physical parameter set, which may reduce the computational load imposed on the first and second decision devices when they perform processing using the MT method.

[0012] (3) In addition to the configuration of (2) above, a condition identification device according to one embodiment of the present invention may have the following configuration: the condition identification device outputs an identification signal indicating whether an engine mounted on a vehicle traveling on a road surface is in a misfire state, the first determiner determines whether the road surface is flat, and the second determiner determines whether intermittent misfire occurs in one or more cylinders of the engine, and is connected in series with the first determiner and executed after processing by the first determiner.

[0013] When the road surface is uneven and bumpy, fluctuations in a specific physical parameter indicating the engine state, such as fluctuations in engine rotation speed, are similar to those when intermittent misfires occur. Therefore, in order to improve the accuracy of identifying whether or not a misfire is occurring using physical parameters indicating the engine state, it is necessary to distinguish between when the road surface is uneven and bumpy and when intermittent misfires occur. With this configuration, the first determiner determines whether or not the road surface is flat using the MT method, thereby reducing the computational load on the condition identification device and improving the accuracy of the second determiner in identifying whether or not a misfire is occurring. Therefore, while improving the accuracy of identifying whether or not an engine is misfiring, the design flexibility of the hardware resources of the condition identification device for identifying whether or not an engine is misfiring can be further increased. Note that sporadic misfires in one cylinder refer to intermittent misfires occurring in one cylinder in an engine having at least one cylinder. In addition, sporadic misfires occurring in multiple cylinders means that misfires occur irregularly in multiple cylinders, such as when the misfiring cylinder among the multiple cylinders changes over time.

[0014] (4) In addition to the configuration of (3) above, a condition identification device according to one embodiment of the present invention may have the following configuration: when the first determiner determines that the road surface is flat, the process proceeds to the processing of the second determiner, and the second determiner determines whether or not intermittent misfires occur in the engine; and when the first determiner determines that the road surface is not flat, the process of the condition identification device is terminated without proceeding to either the processing of the second determiner or the processing for outputting the identification signal, or the process of the first determiner is transitioned to a loop.

[0015] According to this configuration, if the first determiner determines that the road surface is not flat, the processing of the condition identification device is terminated without proceeding to either the process of determining whether or not intermittent misfires occur in the engine by the second determiner or the process of outputting an identification signal by the first determiner, or the processing of the first determiner is transitioned to a loop. Therefore, when the road surface is uneven and not flat, which is similar to the engine condition when intermittent misfires occur, the unnecessary determination of whether or not intermittent misfires occur by the second determiner can be eliminated, thereby reducing the computational load of the processing of the condition identification device. This further increases the design flexibility of hardware resources. Note that the configurations (3) and (4) may also include a third determiner that uses the Mahalanobis-Taguchi algorithm to determine whether or not continuous misfires occur in a specific cylinder of the engine. This third determiner may be connected in parallel with the first determiner or connected in series with the first determiner so that the processing is executed before or after the first determiner.

[0016] In the present invention and embodiments, the monitored object is not particularly limited. For example, the monitored object may be a device or a part of a device. For example, the monitored object may be a living thing (e.g., a human) or a part of a living thing. The monitored object is not limited to an object. For example, the monitored object may be a phenomenon.

[0017] In the present invention and the embodiments, the use of the state identification device is not particularly limited, and the state identification device may be composed of a plurality of devices that can communicate with each other.

[0018] In the present invention and embodiments, the processor includes any circuit, such as a microcontroller, a central processing unit (CPU), a microprocessor, a multiprocessor, an application-specific integrated circuit (ASIC), a programmable logic circuit (PLC), or a field-programmable gate array (FPGA). The memory device is operably coupled to the processor and stores a program executed by the processor. The program causes the processor to execute various processes in the state identification device. The memory device also stores data of a preset unit space. The memory device includes a non-transitory storage medium that stores the program and the data of the unit space. The memory device includes semiconductor memory such as a register or cache memory, a main memory (main memory device / RAM), and storage (external memory device / auxiliary memory device).

[0019] In the present invention and embodiments, a state identification device that outputs an identification signal indicating whether the state of the monitored object belongs to a single predetermined state means a state identification device that identifies (determines) whether the state of the monitored object belongs to a single predetermined state and outputs an identification signal indicating whether the state of the monitored object belongs to a single predetermined state.

[0020] In the present invention and its embodiments, the process of outputting an identification signal indicating whether the state of the monitored object belongs to a single predetermined state based on the judgment result of at least one of a plurality of judgers is one of the following two processes: A process of determining whether the state of the monitored object belongs to a single predetermined state based on the judgment result of one judger. A process of determining whether the state of the monitored object belongs to a single predetermined state based on the judgment results of a plurality of judgers. In the process of determining whether the state of the monitored object belongs to a single predetermined state based on the judgment results of a plurality of judgers, the plurality of judgers determine whether different conditions are met for determining whether the state of the monitored object belongs to a single predetermined state.

[0021] In the present invention and embodiments, the state identification device outputs at least an identification signal indicating that the state of the monitored object belongs to a single predetermined state. Outputting an identification signal indicating whether the state of the monitored object belongs to a single predetermined state may mean outputting different signals when it is determined that the state of the monitored object belongs to a single predetermined state and when it is determined that the state of the monitored object does not belong to a single predetermined state. Outputting an identification signal indicating whether the state of the monitored object belongs to a single predetermined state may mean outputting a signal only when it is determined that the state of the monitored object belongs to a single predetermined state. In this case, the state identification device does not output a signal indicating that the state of the monitored object does not belong to a single predetermined state.

[0022] In the present invention and embodiments, outputting an identification signal may mean outputting the identification signal to a device external to the state identification device, or may mean outputting the identification signal to the state identification device. Outputting an identification signal to the state identification device may mean outputting the identification signal to a processor that causes the state identification device to execute various processes, or may mean outputting the identification signal to a processor included in the state identification device that is different from the processor that causes the state identification device to execute various processes.

[0023] In the present invention and embodiments, the multiple decision makers may be discrimination decision makers or condition decision makers. The discrimination decision maker is a decision maker that determines whether the state of the monitored object belongs to a single predetermined state. The condition decision maker is a decision maker that determines whether a predetermined condition is satisfied, which is not a decision as to whether the state of the monitored object belongs to a single predetermined state. At least the second decision maker of the first and second decision makers may be a discrimination decision maker. At least the first decision maker of the first and second decision makers may be a condition decision maker.

[0024] In the present invention and embodiments, the detector is a detector that monitors a monitoring target and includes various sensors. The multiple physical parameters acquired from at least one detector monitoring the monitoring target may be physical parameters related to the monitoring target, or may be physical parameters related to the environment surrounding the monitoring target, for example. In the present invention and embodiments, the multiple physical parameters are parameters related to multiple types of physical quantities. In the present invention and embodiments, the parameter set is one or more physical parameters selected from the multiple physical parameters and used for judgment by the judgment device. In other words, the multiple physical parameters can be considered judgment target data related to multiple types of physical quantities. The parameter set is set for each judgment device that uses the MT method. In the present invention and embodiments, at least some physical parameters included in the first parameter set and the second parameter set may be the same. In other words, the multiple physical parameters included in the first parameter set and the multiple physical parameters included in the second parameter set may all be the same. Alternatively, the multiple physical parameters included in the first parameter set and the multiple physical parameters included in the second parameter set may be partially the same. Alternatively, the multiple physical parameters included in the first parameter set and the multiple physical parameters included in the second parameter set may all be different. In the present invention and embodiments, the physical parameter may be data acquired from a single detector, data generated by the state identification device from a signal acquired from a single detector, or data generated by the state identification device from multiple signals acquired from multiple detectors. The physical parameter may include, for example, data of a signal output from a sensor (detector). The physical parameter may include, for example, data generated by the state identification device from a signal output from a sensor (detector). The physical parameter may include, for example, data of a signal generated by a control device (detector) that performs control different from the state identification device from a signal output from a sensor, and output from the control device.The physical parameters may include, for example, image data generated by capturing an image using a camera included in an imaging device (detector). The image data is data related to physical parameters such as brightness. The physical parameters may include, for example, time-series data. The number of types of multiple physical parameters acquired by one determiner may be the same as, or may be less than, or greater than, the number of detectors acquiring the multiple physical parameters. When different types of detectors are used to acquire two physical parameters, at least some of the types of physical quantities in the two physical parameters differ from each other. However, when at least some of the types of physical quantities in the two physical parameters differ from each other, the types of detectors used to acquire the two physical parameters do not necessarily have to be different.

[0025] In the present invention and embodiments, the process (A) may be continuously executed during the process (B). That is, the process in which the state identification device acquires a plurality of physical parameters from at least one detector monitoring the monitored object may be executed while the state identification device is executing a process in which a plurality of determiners make a judgment using the acquired plurality of physical parameters.

[0026] In the present invention and its embodiments, the first and second unit spaces set for the first and second decision devices using the MT method are different from each other. A unit space is set for each decision device using the MT method. The unit space is set in advance by the MT method based on a reference data group. The Mahalanobis distance indicates the distance from the unit space. The closer the Mahalanobis distance is to 1, the closer the parameter set to be decided by the decision device is to the reference data group. In the field of quality engineering, where the Mahalanobis distance is used, the square of the Mahalanobis distance is sometimes referred to as the Mahalanobis distance. The reference data group that forms the basis of the unit space used by the decision device may be a data group in which the state of the monitored object belongs to a single predetermined state, or may be a data group in which the state of the monitored object does not belong to a single predetermined state. The unit space is set based on at least one type of feature that indicates the characteristics of the reference data group. The decision device using the MT method extracts at least one type of feature from the parameter set and calculates the Mahalanobis distance based on the extracted at least one type of feature and the unit space. The decision device may use multiple types of feature quantities to calculate one Mahalanobis distance. Even if the physical parameters of the first parameter set and the second parameter set are completely the same, the first decision device and the second decision device may use different unit spaces to calculate the Mahalanobis distance. In this case, the difference between the two unit spaces may be, for example, a difference in the type of feature quantity. In this embodiment, the first decision device and the second decision device calculate the Mahalanobis distance independently. Among the multiple decision devices, all decision devices using the MT method may calculate the Mahalanobis distance independently. Calculating the Mahalanobis distance independently means that one decision device calculates the Mahalanobis distance without relying on the Mahalanobis distance calculated by another decision device.

[0027] In the present invention and embodiments, "transitioning to the first determiner so as to loop the processing of the first determiner" may mean looping the processing of the first determiner again after a determination by the first determiner, or looping the processing of the first determiner again after a determination by the first determiner, and then executing a process executed before the processing of the first determiner. Similarly, in the present invention and embodiments, "transitioning to the second determiner so as to loop the processing of the second determiner again after a determination by the second determiner, or looping the processing of the second determiner again after a determination by the second determiner, and then executing a process executed before the processing of the second determiner. In the present invention and embodiments, "looping the processing of the first determiner" means repeating the processing of the first determiner until the comparison result by the first determiner either satisfies or does not satisfy the first condition. Looping the processing of the second decision unit means repeating the processing of the second decision unit until the comparison result by the second decision unit is either a case where the second condition is satisfied or a case where the second condition is not satisfied.

[0028] In the present invention and embodiments, the multiple determiners may include at least one non-MT determiner that makes a determination without using the MT method. The at least one non-MT determiner that makes a determination without using the MT method may include a non-MT determiner that determines whether a state of a monitored object belongs to a single predetermined state. The at least one non-MT determiner that makes a determination without using the MT method may include a non-MT determiner that determines whether a predetermined condition is met that is not a determination of whether a state of a monitored object belongs to a single predetermined state.

[0029] In the present invention, if the number of a certain component is not clearly specified and the component is expressed in singular when translated into English, the present invention may have a plurality of the component, or the present invention may have only one of the component.

[0030] It should be noted that, in the present invention and embodiments, the words including, having, comprising, and their derivatives are used to encompass additional items in addition to the listed items and equivalents thereof.

[0031] Unless otherwise defined, all terms (including technical and scientific terms) used in this specification and the present invention have the same meaning as commonly understood by those skilled in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted to have a meaning consistent with the meaning in the context of the relevant technology and this disclosure, and should not be interpreted in an idealized or overly formal sense.

[0032] It should be noted that in this specification, the term "preferable" is non-exclusive. "Preferable" means "preferably, but not limited to." In this specification, a configuration described as "preferable" at least achieves the above-mentioned effects obtained by the present invention. In this specification, the term "may (may)" is non-exclusive. "may (may)" means "may (may) but is not limited to." In this specification, "may (may)" implicitly includes the possibility that "does not (is not)." In this specification, a configuration described as "may (may)" at least achieves the above-mentioned effects obtained by the present invention.

[0033] Before describing embodiments of the present invention in detail, it is to be understood that the invention is not limited to the details of construction and the arrangement of components set forth in the following description or illustrated in the drawings. The present invention is capable of embodiments other than those described below. The present invention is also capable of embodiments incorporating various variations of the embodiments described below.

[0034] According to the state identification device of the present invention, which identifies the state of a monitored object using multiple judgers that use the MT method, it is possible to ensure high identification accuracy while making the identification process more efficient and further improving the design freedom of hardware resources.

[0035] FIG. 1 is a diagram illustrating the configuration of a condition identification device according to a first embodiment of the present invention. FIGS. 2(a) to 2(c) are flowcharts illustrating the processing executed by a condition identification device according to a modified example of the first embodiment of the present invention. FIGS. 3(a) to 3(e) are flowcharts illustrating the processing executed by a condition identification device according to a modified example of the first embodiment of the present invention. FIG. 4 is a flowchart illustrating the processing executed by a condition identification device according to a second embodiment of the present invention. FIG. 5 is a diagram illustrating the configuration of a condition identification device according to a second embodiment of the present invention. FIG. 6 is a map used by the intermittent misfire identification determiner of the condition identification device according to the second embodiment of the present invention to estimate the misfire rate. FIGS. 7(a) to 7(d) are graphs illustrating the temporal changes in throttle opening, vehicle speed, and engine rotation speed of a vehicle to which the condition identification device according to the second embodiment of the present invention is applied. FIGS. 8(a) to 8(c) are graphs illustrating the temporal changes in throttle opening, vehicle speed, engine rotation speed, and Mahalanobis distance calculated by the condition determiner of a vehicle to which the condition identification device according to the second embodiment of the present invention is applied. Figures 9(a) and 9(b) are graphs showing temporal changes in the misfire rate, intake air volume, engine speed, and Mahalanobis distance calculated by the intermittent misfire discrimination judger of a vehicle to which the state identification device of the second embodiment is applied. Figure 10 is a graph showing an enlarged portion of Figure 9(a). Figures 11(a) and 11(b) are graphs showing temporal changes in the throttle opening, vehicle speed, engine speed, feedback correction coefficient, and Mahalanobis distance calculated by the continuous misfire discrimination judger of a vehicle to which the state identification device of the second embodiment is applied. Figure 12 is a graph showing an enlarged portion of Figure 11(a).

[0036] First Embodiment A condition identification device 1 according to a first embodiment of the present invention will be described with reference to FIG. 1. The condition identification device 1 outputs an identification signal indicating whether or not the condition of a monitored object belongs to a single predetermined condition. The condition identification device 1 includes a processor 2 and a storage device 3 operably coupled to the processor 2. The storage device 3 stores a program P executed by the processor 2. The program P executed by the processor 2 causes the condition identification device 1 to execute various processes. Some of the various processes executed by the condition identification device 1 in accordance with the program P cause the processor 2 to function as multiple determiners 10. The multiple determiners 10 include determiners that make a determination using at least two or more MT methods. The determiners that make a determination using at least two or more MT methods include a first determiner 11 and a second determiner 12.

[0037] The plurality of decision devices 10 in the first embodiment are two devices, a first decision device 11 and a second decision device 12, which are indicated by solid lines in Fig. 1. The plurality of decision devices 10 may be three devices, namely, the first decision device 11, the second decision device 12, and a third decision device 13, which is indicated by a two-dot chain line in Fig. 1. The number of the plurality of decision devices 10 may be four or more. The plurality of decision devices 10 may be condition decision devices or discrimination decision devices.

[0038] The condition identification device 1 is configured to acquire multiple physical parameters from at least one detector 50 that monitors the monitored object. The at least one detector 50 in the first embodiment shown in FIG. 1 is three, including a first detector 51, a second detector 52, and a third detector 53. The number of at least one detector 50 may be one or two, or may be four or more. The condition identification device 1 of the first embodiment shown in FIG. 1 is configured to be directly connected to the first detector 51, the second detector 52, and the third detector 53 and to acquire multiple physical parameters from these multiple detectors 50. The condition identification device 1 may not be directly connected to the at least one detector 50, but may be connected to the at least one detector 50 via another device and acquire multiple physical parameters from this at least one detector 50. Alternatively, the condition identification device 1 may be directly connected to at least one of the multiple detectors 50 and connected to the remaining at least one detector 50 via another device and acquire multiple physical parameters from these multiple detectors 50.

[0039] Next, the processing executed by the state identification device 1 of the first embodiment will be described with reference to Fig. 1. Fig. 1(a) and Fig. 1(b) are flowcharts each showing an example of the processing executed by the state identification device 1 of the first embodiment. However, these are merely examples and do not limit the first embodiment. For example, the determinations of the first determiner 11 and the second determiner 12 in Fig. 1(a) and Fig. 1(b) may be reversed (YES may be NO, and NO may be YES).

[0040] In step S1, the condition identification device 1 performs a process of acquiring a plurality of physical parameters from at least one detector 50 monitoring the monitored object. The condition identification device 1 in FIG. 1 acquires physical parameters DA, DB, and DC indicated by solid lines from a plurality of detectors 51, 52, and 53. Note that the condition identification device 1 may also acquire the physical parameters DA, DB, and DC indicated by solid lines and physical parameters DE and DF indicated by two-dot chain lines in FIG. 1 from a plurality of detectors 50. The acquired plurality of physical parameters are stored in the storage device 3. In the example of FIGS. 1( a) and 1(b), in step S1, the condition identification device 1 acquires a plurality of physical parameters included in a first parameter set D1 and a second parameter set D2 necessary for the first determiner 11 and the second determiner 12 to make a determination. Note that the process of step S1 may be executed as appropriate even while the process of step S2 is being executed. For example, the process of step S1 may be executed at predetermined time intervals, or may be executed each time the process of making a decision in each of the plurality of decision devices 10 is started in step S2.

[0041] In step S2, the condition identification device 1 uses the plurality of physical parameters acquired in step S1 to perform a process of making a judgment in the plurality of determinators 10. In the example of Figures 1(a) and 1(b), in step S2, the state identification device 1 uses the plurality of physical parameters acquired in step S1 to perform a process of making a judgment in the first determinator 11 (step S21) and a process of making a judgment in the second determinator 12 (step S22).

[0042] First, in step S2, each determiner 10 acquires a parameter set D selected from the plurality of physical parameters acquired in step S1. At least some physical parameters of the parameter sets D acquired by any two of the plurality of determiners 10 may overlap with each other. In the condition identification device 1 of FIG. 1 , the first determiner 11 acquires a first parameter set D1 (not shown) including physical parameters DA and physical parameters DB. The second determiner 12 acquires a second parameter set D2 (not shown) including physical parameters DA and physical parameters DC. The third determiner 13 acquires a third parameter set D3 (not shown) including physical parameters DE and physical parameters DF. The second parameter set D2 includes some physical parameters DA of the first parameter set D1. Furthermore, the third parameter set D3 does not include physical parameters included in the first parameter set D1 and the second parameter set D2. Note that the second parameter set D2 may include all physical parameters DA of the first parameter set D1.

[0043] Next, in step S2, each determinator 10 calculates a Mahalanobis distance MD based on a unit space U preset by the MT method and the acquired parameter set D. The number of Mahalanobis distances calculated by one determinator 10 for making a determination may be one or more. The unit space U is configured using a pre-calculated mean vector and a variance-covariance matrix. The unit space U is stored in the storage device 3. The unit spaces U used by the multiple determinators 10 to calculate the Mahalanobis distance MD are different from one another. In the state identification device 1 of FIG. 1, the three determinators 10 each use different unit spaces U1, U2, and U3. In step S2, the multiple determinators 10 calculate the Mahalanobis distance MD1 independently of one another. In the state identification device 1 of FIG. 1, the first determinator 11 calculates the Mahalanobis distance MD1 of the acquired first parameter set D1 in the unit space U1. The second determiner 12 calculates the Mahalanobis distance MD2 of the acquired second parameter set D2 in the unit space U2. The third determiner 13 calculates the Mahalanobis distance MD3 of the acquired third parameter set D3 in the unit space U3.

[0044] Next, in step S2, each determinator 10 compares the calculated Mahalanobis distance MD with a preset threshold to determine whether the calculated Mahalanobis distance MD satisfies a preset condition. The preset condition may be a condition indicating that the state of the monitored object belongs to a single predetermined state, or a condition indicating that the state of the monitored object belongs to a predetermined state different from the single predetermined state. In the state identification device 1 of FIG. 1 , the first determinator 11 compares the calculated Mahalanobis distance MD1 with a first threshold to determine whether the calculated Mahalanobis distance MD2 satisfies a second threshold to determine whether the calculated Mahalanobis distance MD2 satisfies a second threshold. In step S2, each determinator 10 may make a determination based on a single Mahalanobis distance MD, or may, after the number of calculated Mahalanobis distances MD reaches a predetermined number, compare the calculated Mahalanobis distances MD with a preset threshold to determine whether the predetermined condition is satisfied.

[0045] The first determinator 11 compares the calculated Mahalanobis distance MD with a first threshold, and when the comparison result either satisfies or does not satisfy the first condition, performs one of the following processes: The first determinator 11 ends the processing of the state identification device 1 without going through either the processing of any of the multiple determinators 10 or the processing of outputting an identification signal; or the first determinator 11 is shifted to loop the processing of the first determinator 11.

[0046] 1(a), if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 terminates the processing of the state identification device 1 without going through the processing of any of the multiple determinators 10 or the processing of outputting an identification signal. Although not shown, if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 may be shifted to loop the processing of the first determinator 11. On the other hand, in the example of FIG. 1(a), if the comparison result satisfies the first condition (step S21: YES), the processing is shifted to the second determinator 12 in step S22.

[0047] 1(b), if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 transitions to the process of acquiring multiple physical parameters in step S1, so as to loop the process of the first determinator 11. Note that, although not shown, if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 may terminate the process of the state identification device 1 without going through either the process of any of the multiple determinators 10 or the process of outputting an identification signal. On the other hand, in the example of FIG. 1(a), if the comparison result satisfies the first condition (step S21: YES), the first determinator 11 transitions to the process of outputting an identification signal in step S3.

[0048] The second determinator 12 corresponds to at least one of the following determinators (i) and (ii). The second determinator 12 corresponding to (i) is connected in series with the first determinator 11, and is shifted to after the processing of the first determinator 11 when the comparison result by the first determinator 11 either satisfies the first condition or does not satisfy it, the other case. The second determinator 12 corresponding to (ii) performs one of the following processes when the comparison result of comparing the calculated Mahalanobis distance MD with the second threshold either satisfies the second condition or does not satisfy it. The second determinator 12 corresponding to (ii) ends the processing of the state identification device 1 without going through either the processing of any of the multiple determinators 10 or the processing of outputting an identification signal. Alternatively, the second determinator 12 corresponding to (ii) is shifted to loop the processing of the second determinator 12.

[0049] In the example of FIG. 1( a), the second determinator 12 is connected in series with the first determinator 11. That is, in the state identification device 1 of FIG. 1( a), the first determinator 11 performs a determination process before the second determinator 12 performs a determination process. That is, the first determinator 11 and the second determinator 12 are connected in series means that the first determinator 11 and the second determinator 12 are logically or physically connected in series and processed sequentially. The second determinator 12 of FIG. 1( a) corresponds to the determinator (i) above. When the comparison result of the first determinator 11 satisfies the first condition, the second determinator 12 of FIG. 1( a) is shifted to a process after the first determinator 11's processing. The second determinator 12 of FIG. 1( a) shifts to a process of outputting an identification signal whether or not the comparison result of comparing the calculated Mahalanobis distance MD with the second threshold satisfies the second condition. 1A, if the comparison result satisfies the second condition (step S22: YES), the second determiner 12 proceeds to a process of outputting an identification signal in step S3 (S31). On the other hand, if the comparison result does not satisfy the second condition (step S22: NO), the second determiner 12 proceeds to a process of outputting an identification signal in step S3 (S32).

[0050] In the example of FIG. 1( b), the second determinator 12 is connected in parallel with the first determinator 11. That is, in the state identification device 1 of FIG. 1( b), the second determinator 12 can perform a process of making a judgment in parallel with the process of making a judgment in the first determinator 11. In other words, the first determinator 11 and the second determinator 12 being connected in parallel means that the first determinator 11 and the second determinator 12 are logically or physically connected in parallel and perform processing in parallel. The second determinator 12 of FIG. 1( b) corresponds to the determinator (ii) above. In the example of FIG. 1( b), if the comparison result does not satisfy the second condition (step S22: NO), the second determinator 12 transitions to the process of acquiring multiple physical parameters in step S1 so as to loop the processing of the second determinator 12. Although not shown, if the comparison result does not satisfy the second condition (step S22: NO), the second determinator 12 may terminate the processing of the state identification device 1 without going through either the processing of any of the multiple determinators 10 or the processing of outputting an identification signal. On the other hand, in the example of Fig. 1(b), if the comparison result satisfies the second condition (step S22: YES), the second determinator 11 proceeds to the processing of outputting an identification signal in step S3.

[0051] In step S3, the state identification device 1 performs a process of outputting an identification signal indicating whether the state of the monitored object belongs to a single predetermined state based on the judgment result of at least one of the multiple judges 10. In the example of FIG. 1(a), if the comparison result of the second judger 12 satisfies the second condition, the state identification device 1 outputs an identification signal indicating that the state of the monitored object belongs to a single predetermined state (S31). On the other hand, in the example of FIG. 1(a), if the comparison result of the second judger 12 does not satisfy the third condition, the state identification device 1 outputs an identification signal indicating that the state of the monitored object does not belong to a single predetermined state (S32). In the example of FIG. 1(b), if the comparison result of the first judger 11 satisfies the first condition or if the comparison result of the second judger 12 satisfies the second condition, the state identification device 1 outputs an identification signal indicating that the state of the monitored object belongs to a single predetermined state (S3). Although not shown, in the example of Figure 1(b), if the comparison result of the first determiner 11 satisfies the first condition, an identification signal indicating that the state of the monitored object belongs to a single predetermined state may be output, and if the comparison result of the second determiner 12 satisfies the second condition, an identification signal indicating that the state of the monitored object does not belong to a single predetermined state may be output.

[0052] Modified examples of the processing executed by the state identification device 1 will be described using the flowcharts of Figures 2(a) to 2(c). The second determinator 12 in Figures 2(a) to 2(c) is connected in series with the first determinator 11, similar to Figure 1(a) of the first embodiment. However, Figures 2(a) to 2(c) are merely examples of modified examples of Figure 1(a) of the first embodiment, and do not limit the first embodiment. Furthermore, step S1 is the same processing as described above, and description thereof will be omitted.

[0053] 2A, if the comparison result does not satisfy the first condition (step S21: NO), the first determiner 11 transitions to the process of acquiring multiple physical parameters in step S1, so as to loop the process of the first determiner 11. Although not shown, if the comparison result does not satisfy the first condition (step S21: NO), the first determiner 11 may terminate the process of the state identification device 1 without going through either the process of any of the multiple determiners 10 or the process of outputting an identification signal. On the other hand, if the comparison result satisfies the first condition (step S21: YES), the process is transferred to the second determiner 12. If the comparison result satisfies the second condition (step S22: YES), the second determiner 12 transitions to the process of outputting an identification signal in step S3. If the comparison result does not satisfy the second condition (step S22: NO), the second determiner 12 transitions to the process of acquiring a plurality of physical parameters in step S1 so as to loop the process of the second determiner 12. The second determiner 12 in Fig. 2(a) corresponds to the determiner (i) and the determiner (ii) above.

[0054] 2B, if the comparison result does not satisfy the first condition (step S21: NO), the first determiner 11 transitions to the process of acquiring multiple physical parameters in step S1, so as to loop the process of the first determiner 11. Although not shown, if the comparison result does not satisfy the first condition (step S21: NO), the first determiner 11 may terminate the process of the state identification device 1 without going through either the process of any of the multiple determiners 10 or the process of outputting an identification signal. On the other hand, if the comparison result satisfies the first condition (step S21: YES), the process is transferred to the second determiner 12. If the comparison result satisfies the second condition (step S22: YES), the second determiner 12 transitions to the process of outputting an identification signal in step S3. If the comparison result does not satisfy the second condition (step S22: NO), the second determiner 12 transitions to the process of acquiring a plurality of physical parameters in step S1 so as to loop the process of the second determiner 12. The second determiner 12 in Fig. 2(b) corresponds to the determiner (i) and the determiner (ii) above.

[0055] In the example of FIG. 2( c), if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 terminates the processing of the state identification device 1 without passing through the processing of any of the multiple determinators 10 or the processing of outputting an identification signal. Although not shown, if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 may be shifted to loop its processing. On the other hand, if the comparison result satisfies the first condition (step S21: YES), the second determinator 12 shifts the processing to the processing of outputting an identification signal in step S3. If the comparison result does not satisfy the second condition (step S22: NO), the second determinator 12 terminates the processing of the state identification device 1 without passing through the processing of any of the multiple determinators 10 or the processing of outputting an identification signal. The second decision unit 12 in FIG. 2(c) corresponds to the decision unit (i) and the decision unit (ii) above.

[0056] Modified examples of the processing executed by the state identification device 1 will be described using the flowcharts of Figures 3(a) to 3(e). The state identification device 1 of Figures 3(a) to 3(e) has a first determinator 11, a second determinator 12, and a third determinator 13. However, Figures 3(a) to 3(e) are merely examples of modified examples of the first embodiment and do not limit the first embodiment. Furthermore, steps S1 and S3 are the same processing as described above, and their description will be omitted.

[0057] In the example of FIG. 3A , the second determinator 12 is connected in series with the first determinator 11. The third determinator 13 is also connected in series with the second determinator 12. If the comparison result satisfies the first condition (step S21: YES), the first determinator 11 shifts the processing to the second determinator 12. On the other hand, if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 shifts the processing to the processing of acquiring multiple physical parameters in step S1, so as to loop the processing of the first determinator 11. If the comparison result satisfies the second condition (step S22: YES), the second determinator 12 shifts the processing to the processing of outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the second condition (step S22: NO), the processing is shifted to the third determinator 13. If the comparison result satisfies the third condition (step S23: YES), the third determiner 13 transitions to processing for outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the third condition (step S23: NO), the third determiner 13 transitions to processing for acquiring multiple physical parameters in step S1, so as to loop the processing of the third determiner 13. The second determiner 12 in FIG. 3( a) corresponds to the determiner (i) above. Note that in the example of FIG. 3( a), if the second determiner 12 is replaced with the third determiner 13 and the third determiner 13 is replaced with the second determiner 12, the replaced second determiner 12 corresponds to the determiner (ii).

[0058] In the example of FIG. 3B , the third determinator 13 is connected in series with the first determinator 11. The second determinator 12 is also connected in series with the first determinator 11. If the comparison result satisfies the third condition (step S23: YES), the third determinator 13 transitions to processing for outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the third condition (step S23: NO), the third determinator 13 transitions to processing by the first determinator 11. If the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 transitions to processing for acquiring multiple physical parameters in step S1, looping the processing of the first determinator 11. On the other hand, if the comparison result satisfies the first condition (step S21: YES), the processing is transitioned to processing by the second determinator 12. If the comparison result satisfies the second condition (step S22: YES), the second determiner 12 shifts to processing for outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the second condition (step S22: NO), the second determiner 12 shifts to processing for acquiring a plurality of physical parameters in step S1 so as to loop the processing of the second determiner 12. The second determiner 12 in FIG. 3B corresponds to the determiner (i) and the determiner (ii) above.

[0059] In the example of FIG. 3( c), the second determinator 12 is connected in series with the first determinator 11. The third determinator 13 is connected in series with the first determinator 11. The second determinator 12 and the third determinator 13 are connected in parallel. If the comparison result satisfies the first condition (step S21: YES), the first determinator 11 transitions to the processing of the second determinator 12 and the third determinator 13. On the other hand, if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 transitions to the processing of acquiring multiple physical parameters in step S1 so as to loop the processing of the first determinator 11. If the comparison result satisfies the second condition (step S22: YES), the second determinator 12 transitions to the processing of outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the second condition (step S22: NO), the second determiner 12 shifts the process to a process of acquiring multiple physical parameters in step S1, causing the process of the second determiner 12 to loop. If the comparison result satisfies the third condition (step S23: YES), the third determiner 13 shifts the process to a process of outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the third condition (step S23: NO), the third determiner 13 shifts the process to a process of acquiring multiple physical parameters in step S1, causing the process of the third determiner 13 to loop. The second determiner 12 in FIG. 3C corresponds to the determiner (i) and the determiner (ii) above.

[0060] In the example of FIG. 3( d ), the third determinator 13 is connected in series with the first determinator 11. The third determinator 13 transitions to the processing of the first determinator 11 when the comparison result satisfies the third condition (step S23: YES). On the other hand, the third determinator 13 transitions to the processing of the second determinator 12 when the comparison result does not satisfy the third condition (step S23: NO). The first determinator 11 transitions to the processing of outputting an identification signal in step S3 when the comparison result satisfies the first condition (step S21: YES). On the other hand, the first determinator 11 transitions to the processing of acquiring a plurality of physical parameters in step S1, so as to loop the processing of the first determinator 11. If the comparison result satisfies the second condition (step S22: YES), the second determiner 12 shifts to processing for outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the second condition (step S22: NO), the second determiner 12 shifts to processing for acquiring a plurality of physical parameters in step S1 so as to loop the processing of the second determiner 12. The second determiner 12 in Fig. 3(d) corresponds to the determiner (ii) above.

[0061] In the example of FIG. 3( e), the second determinator 12 is connected in series with the first determinator 11. The third determinator 13 is also connected in series with the second determinator 12. If the comparison result satisfies the first condition (step S21: YES), the first determinator 11 transitions to processing by the second determinator 12. On the other hand, if the comparison result does not satisfy the first condition (step S21: NO), the first determinator 11 transitions to processing for acquiring multiple physical parameters in step S1, so as to loop the processing of the first determinator 11. If the comparison result satisfies the second condition (step S22: YES), the second determinator 12 transitions to processing for outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the second condition (step S22: NO), the second determinator 12 transitions to processing by the third determinator 13. If the comparison result satisfies the third condition (step S23: YES), the third determiner 13 shifts to processing of outputting an identification signal in step S3. On the other hand, if the comparison result does not satisfy the third condition (step S23: NO), the third determiner 13 shifts to processing of acquiring a plurality of physical parameters in step S1 so as to loop the processing of the third determiner 13. The second determiner 12 in Fig. 3(e) corresponds to the determiner in (i) above.

[0062] The MT method is one of the techniques included in the MT system. In addition to the MT method, other major techniques included in the MT system include the MTA method, the RT method, and the two-sided T method. The RT method is a method suitable for setting multiple unit spaces and identifying which of multiple states the state of the monitored object belongs to; however, it is also possible to set only one unit space. However, the RT method is a method suitable for identifying multiple states by setting multiple unit spaces based on the same type of feature, but is not suitable for changing the type of feature for each unit space. Furthermore, the RT method and the MTA method have difficulty in handling the adjoint Mahalanobis distance used in the calculation process. Furthermore, the two-sided T method and the MTA method require setting the unit space and signal level, making it difficult to ensure identification accuracy. In contrast, the state identification device 1 of this embodiment uses multiple judgers that independently perform judgments using the MT method to determine whether the state of the monitored object belongs to a single predetermined state, thereby reducing the load of calculation processing and improving identification accuracy.

[0063] Second Embodiment A condition identification device 1 according to a second embodiment of the present invention will be described with reference to Figures 4 to 13. The condition identification device 1 according to the second embodiment has the same configuration as the condition identification device 1 according to the first embodiment. The condition identification device 1 according to the second embodiment is an example in which the condition identification device according to the present invention is applied to a misfire diagnosis device that outputs an identification signal indicating whether or not the engine 40 mounted on a vehicle 30 is in a misfire state. However, the application of the condition identification device according to the present invention to a misfire diagnosis device is not limited to the second embodiment.

[0064] The condition identification device 1 is provided on a vehicle 30. The vehicle 30 is not particularly limited as long as it is a vehicle 30 that travels on a road surface. The vehicle 30 has a plurality of wheels 31 including at least one drive wheel. The drive wheel receives power output from an engine 40 and rotates.

[0065] As shown in FIG. 5 , the vehicle 30 includes an engine 40, a fuel supply device (not shown), an ignition device (not shown), a control device (not shown), a throttle valve 45, a catalyst 46, an engine rotation speed sensor 51, a throttle opening sensor (throttle position sensor) 52, an intake pressure sensor 53, an oxygen sensor 54, and a wheel rotation speed sensor 55. The vehicle 30 also includes a warning lamp (not shown) that is turned on when the condition identification device 1 outputs an identification signal indicating that the engine 40 is in a misfire state. The condition identification device 1 performs processing to acquire multiple physical parameters from the control device (not shown), the engine rotation speed sensor 51, the throttle opening sensor 52, the intake pressure sensor 53, the oxygen sensor 54, and the wheel rotation speed sensor 55, which correspond to detectors 50 that monitor the vehicle 30 as a monitoring target. In this embodiment, the control device is provided separately from the condition identification device 1, but the condition identification device 1 may also function as the control device.

[0066] The engine 40 has at least one combustion chamber 41. The engine 40 may be a single-cylinder engine or a multi-cylinder engine. An ignition device (not shown) is provided in the combustion chamber 41. The engine 40 has a crankshaft 42 that rotates when a mixture of fuel and air is burned in the at least one combustion chamber 41. Power of the engine 40 is output from the crankshaft 42. A fuel supply device (not shown) is disposed in the combustion chamber 41 or in an intake passage 43 connected to the combustion chamber 41. The fuel supply device injects fuel into the combustion chamber 41 or the intake passage 43. A throttle valve 45 is provided to adjust the amount of air supplied to the engine 40. The throttle valve 45 may be electronically controlled or mechanically controlled.

[0067] The catalyst 46 is disposed in the exhaust passage 44 connected to the combustion chamber 41, and purifies the exhaust gas emitted from the engine 40. The oxygen sensor 54 is provided in the exhaust passage 44, and is located upstream of the catalyst 46 in the flow direction of the exhaust gas. The oxygen sensor 54 outputs a signal corresponding to the oxygen concentration in the exhaust gas. The oxygen sensor 54 outputs a signal indicating whether the oxygen concentration is higher or lower than a predetermined oxygen concentration range. The condition identification device 1 is connected to the oxygen sensor 54. The condition identification device 1 acquires a signal corresponding to the oxygen concentration in the exhaust gas from the oxygen sensor 54.

[0068] The engine rotation speed sensor 51 outputs a signal every time the crankshaft 42 rotates a predetermined angle. In other words, it outputs a signal every predetermined crank angle. The predetermined crank angle may be, for example, 15° crank angle (hereinafter abbreviated as °CA). The condition identification device 1 is connected to the engine rotation speed sensor 51. The condition identification device 1 acquires a signal every predetermined crank angle from the engine rotation speed sensor 51. The condition identification device 1 calculates the engine rotation speed ES, which is the rotation speed of the crankshaft 42, based on the signal output from the engine rotation speed sensor 51.

[0069] The throttle opening sensor 52 detects the position of the throttle valve 45 and outputs a signal representing the opening degree TH of the throttle valve 45. Hereinafter, the opening degree TH of the throttle valve 45 will be referred to as the throttle opening degree TH. The state identification device 1 is connected to the throttle opening sensor 52. The state identification device 1 acquires a signal representing the throttle opening degree TH from the throttle opening sensor 52. The intake pressure sensor 53 is disposed between the throttle valve 45 and the combustion chamber 41 and detects the pressure of air in the intake passage 43. The state identification device 1 is connected to the throttle opening sensor 52. The state identification device 1 acquires a signal representing the pressure of air in the intake passage 43 from the throttle opening sensor 52. The state identification device 1 calculates the intake air amount IA based on, for example, the calculated engine rotation speed ES, the signal from the throttle opening sensor 52, and the signal from the intake pressure sensor 53. The vehicle 30 may have an air flow meter (not shown) that detects the intake air amount IA. In this case, the state identifying device 1 is connected to an air flow meter, and acquires a signal representing the intake air amount IA from the air flow meter.

[0070] The control device controls the amount of fuel supplied from the fuel supply device to the combustion chamber 41. The control device controls the amount of fuel based on a signal from the oxygen sensor 54 to maintain the air-fuel ratio of the mixture near a target air-fuel ratio. The control device sets the amount of fuel based on at least a base fuel amount and a feedback correction coefficient FB set based on the signal from the oxygen sensor 54. The control device may set the amount of fuel based on the base fuel amount, the feedback correction coefficient FB, and at least one correction value. The base fuel amount is set based on a calculated or detected intake air amount IA, etc. When the control device calculates the amount of fuel, the feedback correction coefficient FB is multiplied by the base fuel amount. If the oxygen sensor 54 outputs a signal indicating that the oxygen concentration is higher than a predetermined oxygen concentration range, the control device increases the feedback correction coefficient FB to increase the amount of fuel. If the oxygen sensor 54 outputs a signal indicating that the oxygen concentration is lower than the predetermined oxygen concentration range, the control device decreases the feedback correction coefficient FB to decrease the amount of fuel. The feedback correction coefficient FB fluctuates around a value of 1, for example. The state identification device 1 is connected to the control device. The state identification device 1 acquires the feedback correction coefficient FB and the fuel amount including the base fuel amount from the control device.

[0071] The wheel rotation speed sensor 55 detects the rotation speed of the wheel 31. The state identification device 1 is connected to the wheel rotation speed sensor 55. The state identification device 1 acquires a signal indicating the rotation speed of the wheel 31 from the wheel rotation speed sensor 55. The state identification device 1 calculates the rotation speed of the wheel 31 based on the signal output from the wheel rotation speed sensor 55. The state identification device 1 calculates the vehicle speed VS based on the calculated rotation speed of the wheel 31.

[0072] In the second embodiment, the number of the multiple determiners 10 is three (see FIG. 1 ). The three determiners 10 are composed of a first determiner 11, a second determiner 12, and a third determiner 13. The first determiner 11 is a condition determiner that determines whether the road surface on which the vehicle 30 is traveling is flat. The second determiner 12 and the third determiner 13 determine whether the engine 40 is in a misfire state. The second determiner 12 is an intermittent misfire determination device that determines whether the engine 40 is in a misfire state by determining whether intermittent misfires occur based on the calculated Mahalanobis distance MD. Intermittent misfires are a phenomenon in which misfires occur sporadically in one or more cylinders. The third determiner 13 is a consecutive misfire determination device that determines whether the engine 40 is in a misfire state by determining whether consecutive misfires occur based on the calculated Mahalanobis distance MD. Consecutive misfires are a phenomenon in which misfires occur consecutively in a specific cylinder.

[0073] The condition identification device 1 of the second embodiment executes the determination process by the three determiners 10 in the order shown in FIG. 4 . As shown in FIG. 4 , the second determiner 12 is connected in series with the first determiner 11. The third determiner 13 is connected in parallel with the first determiner 11 and the second determiner 12. If the first determiner 11 determines that the road surface is flat (YES in step S21), the second determiner 12 determines whether the engine 40 is in a misfire state due to intermittent misfire (step S22). If the first determiner 11 determines that the road surface is not flat (NO in step S21), the first determiner 11 does not determine whether the engine 40 is in a misfire state due to intermittent misfire using the second determiner 12, and transitions to the process of acquiring multiple physical parameters in step S1, so as to loop the process of the first determiner 11. If the second determinator 12 determines that the engine 40 is in a misfire state due to intermittent misfire (step S22: YES), the second determinator 12 transitions to a process of outputting an identification signal indicating that the engine 40 is in a misfire state (step S3). On the other hand, if the second determinator 12 determines that the engine 40 is not in a misfire state due to intermittent misfire (step S21: YES), the second determinator 12 transitions to a process of acquiring multiple physical parameters in step S1. The third determinator 13 is connected in parallel with the first determinator 11 and the second determinator 12, and therefore determines whether the engine 40 is in a misfire state due to continuous misfire (step S23), without the first determinator 11 determining whether the road surface is flat. If the third determinator 13 determines that the engine 40 is in a misfire state due to continuous misfire (step S23: YES), the third determinator 13 outputs an identification signal indicating that the engine 40 is in a misfire state (step S3). On the other hand, if the third determiner 13 determines that the engine 40 is not in a misfire state due to consecutive misfires (step S23: NO), the process proceeds to the process of acquiring the plurality of physical parameters in step S1. The second determiner 12 in FIG. 4 corresponds to the determiner (i) and the determiner (ii) above.In the condition identification device 1 of the second embodiment, when the first determiner 11, which is a condition determiner, determines that the road surface is flat, the second determiner 12, which is an intermittence determination determiner, determines whether the engine 40 is in a misfire state, and when the first determiner 11 determines that the road surface is not flat, the second determiner 12, which is an intermittence determination determiner, does not determine whether the engine 40 is in a misfire state. Moreover, regardless of whether the road surface is flat, the third determiner 13, which is a continuity determination determiner, determines whether the engine 40 is in a misfire state.

[0074] The state identification device 1 of the second embodiment may execute the determination process by the three determiners 10 in the order shown in FIG. 3( c ) and FIG. 3( e ), for example.

[0075] The first determiner 11, which is a condition determiner, acquires a vehicle speed VS obtained from the signal of the wheel rotation speed sensor 55 and an engine rotation speed ES obtained from the signal of the engine rotation speed sensor 51 as a first parameter set D selected from the acquired multiple physical parameters. The first determiner 11 may acquire the rotation speed of the wheels 31 obtained from the signal of the wheel rotation speed sensor 55 instead of the vehicle speed VS. The engine rotation speed ES acquired by the first determiner 11 may be a value for each crank angle greater than the crank angle interval at which the engine rotation speed sensor 51 outputs a signal. The engine rotation speed ES acquired by the first determiner 11 may be data of values ​​for each 720° CA, for example. The first determiner 11 extracts multiple types of feature quantities from the first parameter set D1 and calculates a Mahalanobis distance MD based on the extracted multiple types of feature quantities and a predetermined unit space U. Specific examples of feature quantities will be described later. The unit space U for the first determinator 11 is set based on a reference data group for when the road surface is uneven and has bumps and no misfires occur. The first determinator 11 determines that the road surface is not flat when the calculated Mahalanobis distance MD is smaller than a predetermined determination threshold, and determines that the road surface is flat when the calculated Mahalanobis distance MD is equal to or larger than the predetermined determination threshold.

[0076] The first determiner 11 extracts at least one type of feature quantity indicating a characteristic of fluctuations in the engine rotation speed ES from data on the engine rotation speed ES during a first determination period. The length of the first determination period may be set independently of the engine rotation speed ES or may be set according to the engine rotation speed ES. The first determination period may be, for example, approximately one second. The at least one type of feature quantity may be, for example, a first feature quantity indicating the magnitude of fluctuations in the engine rotation speed ES and a second feature quantity indicating the frequency of fluctuations in the engine rotation speed ES. The first feature quantity may be, for example, the difference between the maximum and minimum values ​​of the value for each first unit period during the first determination period. The first unit period may be, for example, approximately 10 to 30 msec. The second feature quantity may be, for example, the standard deviation of the differential value for each second unit period during the first determination period. The length of the second unit period may be the same as or different from the length of the first unit period. The second unit period may be, for example, approximately 10 to 30 msec. The second unit period may be set in accordance with the cycle of fluctuations in the engine speed ES so that a large derivative value appears.

[0077] The first determiner 11 extracts at least one type of feature quantity indicating the characteristics of fluctuations in the vehicle speed VS (or the rotation speed of the wheels 31) from data on the vehicle speed VS (or the rotation speed of the wheels 31) during the first determination period. The at least one type of feature quantity is, for example, a first feature quantity indicating the magnitude of fluctuations in the vehicle speed VS and a second feature quantity indicating the frequency of fluctuations in the vehicle speed VS. A specific example of the first feature quantity may be the same as the specific example of the first feature quantity indicating the magnitude of fluctuations in the engine rotation speed ES described above. A specific example of the second feature quantity may be the same as the specific example of the second feature quantity indicating the frequency of fluctuations in the engine rotation speed ES described above.

[0078] The second determiner 12, which is an intermittent misfire identification determiner, selects from the acquired physical parameters a calculated or detected intake air amount IA and an engine speed ES obtained from a signal from the engine speed sensor 51 as a second parameter set D2. The engine speed ES acquired by the second determiner 12 may be a value for each crank angle greater than the crank angle interval at which the engine speed sensor 51 outputs a signal, similar to the engine speed ES acquired by the first determiner 11. The second determiner 12 extracts multiple types of feature quantities from the second parameter set D2 and calculates a Mahalanobis distance MD based on the extracted multiple types of feature quantities and a preset unit space U. Specific examples of the feature quantities will be described later. The unit space U for the second determiner 12 is set based on a reference data group for when the road surface is flat and no misfire occurs. The second determiner 12 estimates a misfire rate MR based at least on the calculated Mahalanobis distance MD. Because the unit space U is set based on a set of reference data for when no misfire occurs, the misfire rate MR can be estimated from the Mahalanobis distance MD. The misfire rate MR is the ratio of the number of misfires to the cumulative number of revolutions of the crankshaft 42. The second determiner 12 may estimate the misfire rate MR based on the Mahalanobis distance MD and a value related to the engine load. In this case, the storage device 3 pre-stores a map showing the relationship between the Mahalanobis distance MD and the misfire rate MR for each engine load range. The value related to the engine load is, for example, the intake air amount IA. The second determiner 12 may estimate the misfire rate MR based on the Mahalanobis distance MD, the value related to the engine load, and the engine rotation speed ES. In this case, the storage device 3 pre-stores a map showing the relationship between the Mahalanobis distance MD and the misfire rate MR for each engine operating range, as shown in FIG. 6, for example. The engine operating range is a combination of an engine load range and an engine rotation speed range. 6 also shows graphs illustrating the relationship between the Mahalanobis distance MD and the misfire rate MR, which are set for two engine operating regions. In these two graphs, the horizontal axis value X1, which indicates the misfire rate MR, is the same, and the vertical axis value Y1, which indicates the Mahalanobis distance MD, is the same.The second determiner 12 determines that intermittent misfires are occurring when the estimated misfire rate MR is greater than a predetermined misfire rate determination threshold, and determines that intermittent misfires are not occurring when the estimated misfire rate MR is equal to or less than the misfire rate determination threshold. If the second determiner 12 determines that intermittent misfires are occurring, it determines that the engine 40 is in a misfire state and outputs an identification signal indicating that the engine 40 is in a misfire state to an alarm lamp (not shown).

[0079] The second determiner 12 extracts at least one type of feature quantity indicating a characteristic of fluctuations in the engine rotation speed ES from data on the engine rotation speed ES during the second determination period. The length of the second determination period may be the same as or different from the length of the first determination period. The length of the second determination period may be set independently of the engine rotation speed ES or may be set according to the engine rotation speed ES. The at least one type of feature quantity is, for example, a feature quantity indicating the frequency and magnitude of fluctuations in the engine rotation speed ES. The feature quantity indicating the frequency of fluctuations in the engine rotation speed ES may be, for example, a standard deviation of a differential value for each unit period during the second determination period. The at least one type of feature quantity may be a plurality of standard deviations having different unit periods of different lengths. When the feature quantity is a plurality of standard deviations having different unit periods of different lengths, the feature quantity indicates the magnitude of fluctuations in the engine rotation speed ES. For example, the at least one type of feature may be a standard deviation of the derivative values ​​obtained every 10 msec in the second determination period, a standard deviation of the derivative values ​​obtained every 20 msec in the second determination period, and a standard deviation of the derivative values ​​obtained every 30 msec in the second determination period. The second determiner 12 may acquire, as part of the second parameter set D2, at least some of the multiple types of feature values ​​extracted by the first determiner 11 from the data of the engine rotation speed ES.

[0080] The second determiner 12 extracts at least one characteristic amount from the data of the intake air amount IA during the second determination period. The at least one characteristic amount is, for example, a representative value of the intake air amount IA during the second determination period. The representative value may be, for example, an average value.

[0081] The third determinator 13, which is a consecutive misfire identification determinator, selects from the acquired plurality of physical parameters a third parameter set D3, which includes a throttle opening TH obtained from a signal from the throttle opening sensor 52, a vehicle speed VS obtained from a signal from the wheel rotation speed sensor 55, and a feedback correction coefficient FB set based on a signal from the oxygen sensor 54. The third determinator 13 may obtain the rotation speed of the wheels 31 obtained from a signal from the wheel rotation speed sensor 55 instead of the vehicle speed VS. The third determinator 13 may obtain the signal value of the oxygen sensor 54 instead of the feedback correction coefficient FB. The third determinator 13 extracts multiple types of feature quantities from the third parameter set D3 and calculates a Mahalanobis distance MD based on the extracted multiple types of feature quantities and a preset unit space U. Specific examples of the feature quantities will be described later. The unit space U for the third determinator 13 is set based on a reference data group obtained when the road surface is flat and no misfire occurs. The third determinator 13 determines that consecutive misfires are occurring when the calculated Mahalanobis distance MD is greater than a predetermined threshold value greater than 1, and determines that consecutive misfires are not occurring when the calculated Mahalanobis distance MD is less than the threshold value. The unit space U for the third determinator 13 may be set based on a reference data set obtained when the road surface is flat and consecutive misfires are occurring. In this case, the third determinator 13 determines that consecutive misfires are occurring when the calculated Mahalanobis distance MD is less than a predetermined threshold value near 1, and determines that consecutive misfires are not occurring when the calculated Mahalanobis distance MD is greater than the threshold value. Regardless of the setting of the unit space U, the reference data set is preferably, but is not limited to, a data set obtained when the vehicle speed VS is maintained constant. When the third determinator 13 determines that consecutive misfires are occurring, it determines that the engine 40 is in a misfire state and outputs an identification signal indicating that the engine 40 is in a misfire state to an alarm lamp (not shown). When the third determiner 13 determines that continuous misfires are occurring, in addition to outputting the identification signal, it may also output information on the misfire rate MR estimated based on the number of cylinders of the engine 40 to an output destination other than the alarm lamp.For example, if engine 40 is a four-cylinder engine and continuous misfires are occurring, the misfire rate MR can be estimated to be at least 25% because continuous misfires are occurring in at least one of the four cylinders. The misfire rate determination threshold value used by second determiner 12, which is an intermittent misfire identification determiner, is smaller than the misfire rate when continuous misfires occur in one cylinder in engine 40 with a typical number of cylinders. If third determiner 13 is configured to output information about the misfire rate MR when it determines that engine 40 is in a misfire state, second determiner 12 is configured to output information about the estimated misfire rate MR when it determines that engine 40 is in a misfire state.

[0082] The third determiner 13 extracts at least one characteristic quantity indicating the magnitude of the throttle opening TH relative to the vehicle speed VS from the data on the throttle opening TH and the data on the vehicle speed VS (or the rotation speed of the wheels 31) during the third determination period. The length of the third determination period may be the same as or different from the lengths of at least one of the first determination period and the second determination period. The length of the third determination period may be set independently of the engine rotation speed ES or may be set according to the engine rotation speed ES. The at least one characteristic quantity may be, for example, a value obtained by dividing the average value of the throttle opening TH during the third diagnosis period by the average value of the vehicle speed VS during the third diagnosis period.

[0083] The third determiner 13 extracts a feature quantity indicating the characteristics of fluctuations in the feedback correction coefficient FB (or the signal value of the oxygen sensor 54) from the data of the feedback correction coefficient FB (or the signal value of the oxygen sensor 54) during the third determination period. The feature quantity indicating the characteristics of fluctuations in the feedback correction coefficient FB (or the signal value of the oxygen sensor 54) is, for example, a representative value (feature quantity) of the feedback correction coefficient FB (or the signal value of the oxygen sensor 54) during the third determination period and a feature quantity indicating the frequency of fluctuations in the feedback correction coefficient FB (or the signal value of the oxygen sensor 54) during the third determination period. The representative value may be, for example, an average value. The feature quantity indicating the frequency of fluctuations in the feedback correction coefficient FB (or the signal value of the oxygen sensor 54) during the third determination period may be, for example, the standard deviation of the differential value per unit period in the third determination period. The unit period is set to a length shorter than the cycle of fluctuations in the feedback correction coefficient FB. This makes it possible to extract the feature quantity indicating the frequency of fluctuations in the feedback correction coefficient FB. The unit period may be, for example, about 10 to 30 msec. The period of fluctuation of the feedback correction coefficient FB is usually 100 msec or more.

[0084] 7(a) to 7(d) are graphs showing temporal changes in the throttle opening TH obtained from the signal of the throttle opening sensor 52, the vehicle speed VS obtained from the signal of the wheel rotation speed sensor 55, and the engine rotation speed ES obtained from the signal of the engine rotation speed sensor 51. The range of values ​​on the vertical axis of the throttle opening TH graphs in FIGS. 7(a) to 7(d) is the same. The difference between the upper and lower limit values ​​of the vehicle speed VS graphs in FIGS. 7(a) to 7(d) is also the same. The difference between the upper and lower limit values ​​of the engine rotation speed ES graphs in FIGS. 7(a) to 7(d) is also the same. In FIGS. 7(a) to 7(d), the engine rotation speed ES graphs are graphs of values ​​every 720° CA. The time range of the graphs in FIGS. 7(a) to 7(d) is approximately 10 seconds. 7(a) is a graph showing the results when the road surface is not flat, FIG. 7(b) is a graph showing the results when intermittent misfires occur, FIG. 7(c) is a graph showing the results when continuous misfires occur, and FIG. 7(d) is a graph showing the results when the engine is normal. In the description of this embodiment, normal refers to the case when no misfires occur and the road surface is flat.

[0085] As shown in Figures 7(a) to 7(d), regardless of whether misfire occurs, the engine rotation speed ES fluctuates in an oscillating manner in response to the timing of a specific stroke (e.g., the combustion stroke) in one cycle of the engine 40. When intermittent misfire occurs, as shown in Figures 7(b) and 7(d), the fluctuation of the engine rotation speed ES becomes larger than under normal conditions. That is, the amplitude of the fluctuation of the engine rotation speed ES becomes larger. This is because the engine rotation speed ES decreases the instant intermittent misfire occurs, and when ignition returns to normal immediately thereafter, the engine rotation speed ES increases compared to under normal conditions. As shown in Figures 7(a) and 7(d), when the road surface is uneven and has bumps, the contact state between the wheels 31 and the road surface is not constant, and the vehicle separates from the road surface or makes strong contact with the road surface, resulting in larger fluctuations in the rotation speed of the wheels 31. As a result, the crankshaft 42, which is mechanically connected to the drive wheels of the wheels 31, is affected by the fluctuations in the rotation speed of the wheels 31, resulting in larger fluctuations in the engine rotation speed ES. As shown in Figures 7(a) and 7(b), the fluctuations in engine speed ES when the road surface is uneven are similar to those when intermittent misfires occur. However, the fluctuations in the rotational speed of the wheels 31 differ between when the road surface is uneven and when intermittent misfires occur. Therefore, it is possible to distinguish between traveling on an uneven road surface and intermittent misfires using the engine speed ES data and the rotational speed of the wheels 31 or the vehicle speed VS calculated from the rotational speed of the wheels 31. However, if the unit space U for the first determiner 11 is set based on a reference data group for when the road surface is flat and no misfires occur, the Mahalanobis distance MD will be large not only when the road surface is uneven but also when intermittent misfires occur. Therefore, if the first determinator 11 were to determine whether the road surface is flat or whether intermittent misfires have occurred based on this unit space U, the Mahalanobis distance MD would be large in both cases where the road surface is uneven and where intermittent misfires have occurred, and it would be impossible to correctly determine whether the road surface is flat. In this embodiment, the unit space U for the first determinator 11 is set based on a reference data group when the road surface is not flat and no misfires have occurred.This prevents the first determinator 11 from erroneously determining that the road surface is not flat when intermittent misfires are occurring. Furthermore, in this embodiment, the second determinator 12 determines whether intermittent misfires are occurring after the first determinator 11 determines that the road surface is flat. Therefore, even if the unit space U for the second determinator 12 is set based on a set of reference data for when the road surface is flat and no misfires are occurring, the second determinator 12 can correctly determine whether intermittent misfires are occurring.

[0086] When continuous misfires occur, the fluctuations in engine speed ES differ from normal. However, as shown in FIGS. 7(c) and 7(d), this difference cannot be determined from engine speed ES data taken every 720° CA. For this reason, conventional misfire diagnosis uses engine speed ES data with high time resolution. Conventional misfire diagnosis uses engine speed ES data taken every 15° CA, for example. In contrast, in this embodiment, engine speed ES is not used to determine whether continuous misfires occur.

[0087] 8(a) to 8(c) are graphs showing temporal changes in the throttle opening TH obtained from the signal of the throttle opening sensor 52, the vehicle speed VS obtained from the signal of the wheel rotation speed sensor 55, the engine rotation speed ES obtained from the signal of the engine rotation speed sensor 51, and the Mahalanobis distance MD calculated by the first determiner 11. Strictly speaking, the vertical axis of the Mahalanobis distance MD graphs in FIGS. 8(a) to 8(c) represents the square of the Mahalanobis distance MD. The same applies to the vertical axes of the Mahalanobis distance MD graphs in FIGS. 9(a), 9(b), 10, 11(a), 11(b), and 12, which will be described later. The upper limit of the vertical axis of the Mahalanobis distance MD graphs in FIGS. 8(a) to 8(c) is 45. The range of values ​​on the vertical axis of the throttle opening TH graphs in FIGS. 8(a) to 8(c) is the same. Like the throttle opening TH graph, the vehicle speed VS graph and the engine rotation speed ES graph in Figures 8(a) to 8(c) have the same range of values ​​on the vertical axis. The time range of the graphs in Figures 8(b) and 8(c) is approximately 30 minutes. Figures 8(b) and 8(c) are graphs showing values ​​from when the vehicle 30 starts traveling, and the vehicle 30 is driven so that the changes in vehicle speed VS are the same in Figures 8(b) and 8(c). Figure 8(a) is a graph showing a case where the road surface is uneven and no misfire occurs, Figure 8(b) is a graph showing a case where the road surface is flat and intermittent misfire occurs, and Figure 8(c) is a graph showing a normal state. As shown in Figure 8(a), when the road surface is uneven, the Mahalanobis distance MD calculated by the first determinator 11 is distributed near 1. Furthermore, as shown in Figures 8(b) and 8(c), when the road surface is flat, the Mahalanobis distance MD calculated by the first determiner 11 remains greater than 1 regardless of whether a misfire occurs.

[0088] 9(a) and 9(b) are graphs showing temporal changes in the misfire rate MR, intake air amount IA, engine rotation speed ES, and Mahalanobis distance MD calculated by the second determiner 12 when the engine 40 is operated so that intermittent misfires occur at a predetermined misfire rate MR. The upper limit of the vertical axis of the Mahalanobis distance MD graphs in FIGS. 9(a) and 9(b) is 19,000. The range of values ​​on the vertical axis of the misfire rate MR graphs in FIGS. 9(a) and 9(b) is the same. The range of values ​​on the vertical axis of the intake air amount IA graph and the engine rotation speed ES graph, like the misfire rate MR graph, is also the same. The time range of the graphs in FIGS. 9(a) and 9(b) is approximately one minute. FIG. 9(a) is a graph for a low engine load, and FIG. 9(b) is a graph for a high engine load. In Figures 9(a) and 9(b), misfire has not yet occurred during period A1. Comparing Figures 9(a) and 9(b) reveals that the amount of fluctuation in engine speed ES during intermittent misfires is greater under high load conditions than under low load conditions. In other words, engine load correlates with the amount of fluctuation in engine speed ES during intermittent misfires. As shown in Figures 9(a) and 9(b), the magnitude of fluctuation in engine speed ES is not correlated with the misfire rate MR. Since the higher the misfire rate MR, the shorter the time interval between misfires, the higher the frequency of fluctuations in engine speed ES. When the frequency of fluctuations in engine speed ES is high, the lines in the graph of engine speed ES are more closely spaced.

[0089] In this embodiment, the second determiner 12 acquires the intake air amount IA and the engine speed ES as the second parameter set D2, extracts a feature value representing the frequency of fluctuations in the engine speed ES from the engine speed ES data, and calculates the Mahalanobis distance MD based on the extracted feature value representing the frequency of fluctuations in the engine speed ES, a representative value (feature value) of the intake air amount IA, and the unit space U. As shown in FIGS. 9A and 9B, the higher the misfire rate MR, the larger the Mahalanobis distance MD. Therefore, the calculated Mahalanobis distance MD can be used to estimate the misfire rate MR. Furthermore, although the intake air amount IA is included in the second parameter set D2, as shown in FIGS. 9A and 9B, the Mahalanobis distance MD varies depending on the engine load, even for the same misfire rate MR. Therefore, the misfire rate MR can be accurately estimated by estimating the misfire rate MR using the calculated Mahalanobis distance MD and a value related to the engine load (e.g., the intake air amount IA). Furthermore, by estimating the misfire rate MR using the calculated Mahalanobis distance MD, a value related to the engine load (for example, the intake air amount IA), and the engine rotation speed ES, the misfire rate MR can be estimated with higher accuracy.

[0090] Figure 10 is a graph showing three regions with different misfire rates selected from the three graphs in Figure 9(a) excluding the intake air volume IA, and is expanded along the horizontal axis. The upper limit of the vertical axis of the Mahalanobis distance MD graph in Figure 10 is 9000. The period indicated by the arrow in Figure 10 indicates a time range of, for example, 5 seconds. If the second determination period is, for example, 1 second, the Mahalanobis distance MD may not be stable 1 or 2 seconds after the misfire rate MR changes. However, approximately 5 seconds after the misfire rate MR changes, regardless of the engine load, the second determiner 12 can determine that intermittent misfires are occurring and accurately estimate the misfire rate MR.

[0091] 11(a) and 11(b) are graphs showing temporal changes in the throttle opening TH, vehicle speed VS, engine rotation speed ES, feedback correction coefficient FB, and Mahalanobis distance MD calculated by the third determiner 13 after the vehicle 30 starts traveling. The upper limit value of the vertical axis of the graphs of the Mahalanobis distance MD in FIGS. 11(a) and 11(b) is 900. The range of values ​​on the vertical axis of the graphs of the throttle opening TH in FIGS. 11(a) and 11(b) is the same. The graphs of the vehicle speed VS, the engine rotation speed ES, and the feedback correction coefficient FB in FIGS. 11(a) and 11(b) also have the same range of values ​​on the vertical axis, as with the graph of the throttle opening TH. In the examples of FIGS. 11(a) and 11(b), the unit space U for the third determiner 13 is set based on a reference data group when the road surface is flat and no misfire occurs. The time range of the graphs in FIGS. 11(a) and 11(b) is approximately 30 minutes. FIG. 11(a) is a graph showing a case where consecutive misfires are occurring, and FIG. 11(b) is a graph showing a normal state. In FIGS. 11(a) and 11(b), the vehicle 30 is driven so that the changes in vehicle speed VS are the same. When consecutive misfires are occurring, the output of the engine 40 is reduced compared to normal operation. Therefore, as shown in FIGS. 11(a) and 11(b), when consecutive misfires are occurring, the throttle opening TH is larger than under normal operation, even at the same vehicle speed VS. Furthermore, when consecutive misfires are occurring, the feedback correction coefficient FB is higher than under normal operation. In FIG. 11(a), the feedback correction coefficient FB is maintained at its upper limit for a long period of time. In other words, the feedback correction coefficient FB fluctuates less frequently. The reason why the feedback correction coefficient FB becomes high is that, when consecutive misfires occur, the air-fuel mixture is not combusted in a particular cylinder, and even if the fuel amount is increased, the oxygen sensor 54 continues to output a signal indicating that the oxygen concentration is higher than the predetermined range. Focusing on the behavior of physical quantities that occurs when such consecutive misfires occur, the third determiner 13 of this embodiment determines whether or not consecutive misfires are occurring using the vehicle speed VS (or the rotational speed of the wheels 31), the throttle opening TH, and the feedback correction coefficient FB (or the signal from the oxygen sensor 54).As shown in Figure 11(a), when consecutive misfires occur, the Mahalanobis distance MD is distributed over values ​​significantly greater than 1. As shown in Figure 11(b), when consecutive misfires do not occur, the Mahalanobis distance MD is distributed over a range close to 1. In Figure 11(b), there are points where the Mahalanobis distance MD temporarily becomes significantly greater than 1. This occurs when the throttle opening TH suddenly increases due to starting or shifting gears.

[0092] FIG. 12 is a graph of FIG. 11( a) , enlarged in the horizontal direction, showing the region 25 seconds after the vehicle 30 starts traveling. The upper limit value of the vertical axis of the graph of the Mahalanobis distance MD in FIG. 12 is 900. In FIGS. 11( a), 11( b), and 12, the vehicle 30 is stopped in an idling state before starting to travel, and the throttle opening TH is still minimal even 5 seconds after the vehicle 30 starts traveling. Therefore, if continuous misfires occur, the feedback correction coefficient FB begins to increase approximately 5 seconds after the vehicle 30 starts traveling, and the Mahalanobis distance MD becomes a value slightly higher than 1. Then, approximately 10 seconds after the vehicle 30 starts traveling, the Mahalanobis distance MD stabilizes at a value clearly higher than 1. Therefore, in the examples of Figures 11(a) and 12, if the above-mentioned third judgment period is, for example, 1 second, approximately 10 seconds after the vehicle 30 starts to move, the third judger 13 can correctly judge that the engine 40 is in a misfire state and can accurately estimate the misfire rate MR.

[0093] The misfire rate MR threshold, which is the standard for determining whether the engine 40 is misfiring, may be as low as 3%, for example. In a conventional method for calculating the misfire rate MR by counting the number of misfires, the number of misfires is counted during 1,000 revolutions of the crankshaft 42 in order to ensure accuracy in the misfire rate MR. Furthermore, to ensure accuracy, the period during which the engine speed ES changes due to changes in the throttle opening TH is excluded. Therefore, in a conventional misfire diagnosis that does not use the MT method, if the engine speed ES is low, a diagnosis time of approximately several tens of seconds is required to complete 1,000 revolutions.

[0094] The condition identification device 1 of this embodiment focuses on the "visual appearance" of physical quantities related to the operating state of the vehicle 30 when they are graphed, and quantifies the "visual appearance" using the MT method, a pattern recognition technology, to perform misfire diagnosis. Therefore, the first determiner 11 and the second determiner 12 can make a determination without using engine rotation speed ES data with high time resolution, as used in conventional misfire diagnosis without the MT method. The third determiner 13 can also make a determination without using engine rotation speed ES data. Furthermore, the third determiner 13 can also make a determination without using data with high time resolution, as used in conventional misfire diagnosis without the MT method. Therefore, the computational load can be significantly reduced compared to conventional misfire diagnosis without the MT method. Furthermore, in the condition identification device 1 of the second embodiment, the three determiners 10 independently perform determinations using the MT method to determine whether the engine 40 is in a misfire state. Therefore, compared to the condition identification device of Patent Document 4, in which a single determiner uses the MT method to determine whether the engine is misfiring, the calculation processing performed by the single determiner 10 can be simplified. This reduces the calculation processing load on the entire condition identification device 1. This increases the design flexibility of the hardware resources of the condition identification device 1 while further improving the identification accuracy. Because the three determiners 10 of this embodiment use the MT method to make the determination, the lengths of the first, second, and third determination periods can be significantly shorter than those in conventional misfire diagnosis that do not use the MT method. Therefore, the condition identification device 1 of the second embodiment can determine whether the engine 40 is misfiring in real time and accurately estimate the misfire rate MR.

[0095] In addition, the multiple determiners 10 functioning as the processor 2 of the state identification device 1 of the first embodiment may include, in addition to the first to third determiners 11 to 13 that make judgments using the MT method, at least one non-MT determiner (not shown) that makes judgments without using the MT method.

[0096] In the second embodiment, the MT method is used to determine whether an intermittent misfire occurs, whether a continuous misfire occurs, and whether the road is flat. However, it is also possible to use the MT method to determine two of the intermittent misfire, continuous misfire, and whether the road is flat, and not to use the MT method for the remaining one. For example, it is also possible to use the MT method to determine whether an intermittent misfire occurs and whether the road is flat, but not to use the MT method for the continuous misfire determination. It is also possible to use the MT method to determine whether the road is flat and whether the road is continuous, but not to use the MT method for the intermittent misfire determination.

[0097] In the second embodiment, the condition identification device 1 is provided in the vehicle 30, but when the condition identification device of the present invention is applied to a condition identification device that outputs an identification signal indicating whether or not an engine mounted on a vehicle is in a misfire state, the condition identification device may be a device that is not provided in the vehicle but is capable of communicating with a device provided in the vehicle.

[0098] The condition identification device of the present invention can be applied to, for example, quality control systems for production lines, equipment diagnosis systems for large-scale plants, operation control systems for automobiles and aircraft, and anomaly detection systems for data centers as monitored systems. When a quality control system for a production line is monitored, the condition identification device of the present invention is configured, for example, to perform real-time evaluation of multiple quality parameters using multiple judgers. Specifically, the condition identification device is connected to a camera for acquiring image data and includes a first judger that judges whether or not there is a defective product through visual inspection and a second judger that judges whether or not there is a defective product through dimensional inspection. Then, based on the judgment results of steps S21 and S22 performed in the order shown in FIG. 2( c), an identification signal indicating a defective product is output in step S3. This enables continuous monitoring of product quality in high-speed manufacturing processes and reduces manufacturing costs by detecting defective products early.

[0099] Furthermore, when monitoring an equipment diagnostic system for a large-scale plant, the condition identification device of the present invention is configured, for example, to perform real-time analysis of multiple sensor data (data from temperature sensors, pressure sensors, flow rate sensors, vibration sensors, etc.) using multiple decision-makers. This enables early detection of equipment abnormalities and status monitoring for preventive maintenance. When monitoring an operation control system for an automobile, aircraft, or the like, the condition identification device of the present invention is configured, for example, to perform real-time processing of multiple sensor information using multiple decision-makers. This enables immediate detection of abnormal conditions in the operation control system and realizes faster control. Furthermore, when monitoring an anomaly detection system for a data center, the condition identification device of the present invention is configured, for example, to perform constant monitoring of server status using multiple decision-makers. This enables detection of abnormalities in network traffic and efficient use of system resources. Even for these monitoring targets, applying the condition identification device of the present invention, which uses multiple decision-makers that use the MT method to identify the status of the monitoring target, can ensure high identification accuracy, improve the efficiency of the identification process, and further increase the design flexibility of hardware resources. Furthermore, the condition identification device of the present invention can be applied to, for example, a multi-stage quality inspection system on a production line, a security system that performs step-by-step abnormality detection, or a medical diagnostic system that performs step-by-step symptom determination as the object to be monitored.

[0100] 1: State identification device, 2: Processor, 3: Storage device, 10: Decision device, 11: First decision device, 12: Second decision device, 13: Third decision device, 30: Vehicle, 40: Engine, 50, 51, 52, 53: Detector, D: Parameter set, MD: Mahalanobis distance, P: Program, U: Unit space

Claims

1. A condition identification device that outputs an identification signal indicating whether or not a condition of a monitored object belongs to a single predetermined condition, the condition identification device comprising a processor and a storage device operatively coupled to the processor, the storage device storing a program executed by the processor, the program causing the condition identification device to execute the following processes: (A) acquiring a plurality of physical parameters from at least one detector that monitors the monitored object; (B) making a judgment with a plurality of judgers using the acquired plurality of physical parameters; and (C) outputting an identification signal indicating whether or not the condition of the monitored object belongs to the single predetermined condition based on the judgment result of at least one of the plurality of judgers, the plurality of judgers including at least a first judger and a second judger that use the Mahalanobis-Taguchi method, the first decision unit is a decision unit that calculates a Mahalanobis distance of a first parameter set selected from the acquired plurality of physical parameters in a first unit space constructed using a first mean vector and a first variance-covariance matrix that are calculated in advance, and compares the calculated Mahalanobis distance with a first threshold value to decide whether or not a first condition is satisfied, and when the comparison result of the first decision unit either satisfies or does not satisfy the first condition, the first decision unit is shifted to terminating the processing of the state identification device or looping the processing of the first decision unit without going through either the processing of any of the plurality of decision units or the processing of outputting the identification signal; The second determinator is a determinator that calculates a Mahalanobis distance of a second parameter set selected from the acquired physical parameters in a second unit space that is different from the first unit space and that is constructed using a pre-calculated second mean vector and a second variance-covariance matrix, and compares the calculated Mahalanobis distance with a second threshold value to determine whether a second condition is satisfied, and is characterized in that it corresponds to at least one of the determinator (i) and the determinator (ii) below.(i) a determiner connected in series with the first determiner, and transitioned after the processing of the first determiner when the comparison result by the first determiner satisfies or does not satisfy the first condition, (ii) a determiner that, when the comparison result satisfies or does not satisfy the second condition, ends the processing of the state identification device or causes the processing of the second determiner to loop without transitioning to either the processing of any of the plurality of determiners or the processing of outputting the identification signal.

2. The state identification device according to claim 1, wherein said second parameter set includes at least some of the physical parameters of said first parameter set.

3. A state identification device as claimed in any one of claims 1 or 2, characterized in that the state identification device outputs an identification signal indicating whether an engine mounted on a vehicle traveling on a road surface is in a misfire state, the first determiner determines whether the road surface is flat, and the second determiner determines whether there is intermittent misfire, which occurs sporadically in one or more cylinders of the engine, and is connected in series with the first determiner and executed after processing by the first determiner.

4. A condition identification device as described in claim 3, characterized in that, when the first determiner determines that the road surface is flat, the processing proceeds to the second determiner, which determines whether or not there is intermittent misfire in the engine, and when the first determiner determines that the road surface is not flat, the processing of the condition identification device is terminated without proceeding to either the processing of the second determiner or the processing for outputting the identification signal, or the processing of the first determiner is transitioned to a loop.

Images